{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S46HULF6XG6S5IS3KCYXE3K3WM","short_pith_number":"pith:S46HULF6","schema_version":"1.0","canonical_sha256":"973c7a2cbeb9bd2ea25b50b1726d5bb301c75a010e3ad9217fb226989daa37ce","source":{"kind":"arxiv","id":"2201.05867","version":1},"attestation_state":"computed","paper":{"title":"Transferability in Deep Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Junguang Jiang, Mingsheng Long, Yang Shu","submitted_at":"2022-01-15T15:03:17Z","abstract_excerpt":"The success of deep learning algorithms generally depends on large-scale data, while humans appear to have inherent ability of knowledge transfer, by recognizing and applying relevant knowledge from previous learning experiences when encountering and solving unseen tasks. Such an ability to acquire and reuse knowledge is known as transferability in deep learning. It has formed the long-term quest towards making deep learning as data-efficient as human learning, and has been motivating fruitful design of more powerful deep learning algorithms. We present this survey to connect different isolate"},"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":"2201.05867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-15T15:03:17Z","cross_cats_sorted":[],"title_canon_sha256":"b52f92a1f74a4f5c6d19ef4c9af7f3559cce4c9d84c076a0d727132d44069232","abstract_canon_sha256":"de428779010b991b08bcc7f6e1410eea68d94e320de2318e753e2f9705e4d8de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:52.388516Z","signature_b64":"yp1uDjeIX3kUXouoxSfylTPF9UabxGXO9YkpVJD/Sw85Y1qsFjyakvli6N49S8xyBfKWdxIKXVd2gkDMiUt1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"973c7a2cbeb9bd2ea25b50b1726d5bb301c75a010e3ad9217fb226989daa37ce","last_reissued_at":"2026-07-05T03:48:52.388098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:52.388098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferability in Deep Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Junguang Jiang, Mingsheng Long, Yang Shu","submitted_at":"2022-01-15T15:03:17Z","abstract_excerpt":"The success of deep learning algorithms generally depends on large-scale data, while humans appear to have inherent ability of knowledge transfer, by recognizing and applying relevant knowledge from previous learning experiences when encountering and solving unseen tasks. Such an ability to acquire and reuse knowledge is known as transferability in deep learning. It has formed the long-term quest towards making deep learning as data-efficient as human learning, and has been motivating fruitful design of more powerful deep learning algorithms. We present this survey to connect different isolate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05867","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/2201.05867/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":"2201.05867","created_at":"2026-07-05T03:48:52.388146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05867v1","created_at":"2026-07-05T03:48:52.388146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05867","created_at":"2026-07-05T03:48:52.388146+00:00"},{"alias_kind":"pith_short_12","alias_value":"S46HULF6XG6S","created_at":"2026-07-05T03:48:52.388146+00:00"},{"alias_kind":"pith_short_16","alias_value":"S46HULF6XG6S5IS3","created_at":"2026-07-05T03:48:52.388146+00:00"},{"alias_kind":"pith_short_8","alias_value":"S46HULF6","created_at":"2026-07-05T03:48:52.388146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05159","citing_title":"X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00558","citing_title":"Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23028","citing_title":"RADAR: Relative Angular Divergence Across Representations","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2507.12590","citing_title":"From Time-series Generation, Model Selection to Transfer Learning: A Comparative Review of Pixel-wise Approaches for Large-scale Crop Mapping","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2507.22101","citing_title":"AI in Agriculture: A Survey of Deep Learning Techniques for Crops, Fisheries and Livestock","ref_index":287,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S46HULF6XG6S5IS3KCYXE3K3WM","json":"https://pith.science/pith/S46HULF6XG6S5IS3KCYXE3K3WM.json","graph_json":"https://pith.science/api/pith-number/S46HULF6XG6S5IS3KCYXE3K3WM/graph.json","events_json":"https://pith.science/api/pith-number/S46HULF6XG6S5IS3KCYXE3K3WM/events.json","paper":"https://pith.science/paper/S46HULF6"},"agent_actions":{"view_html":"https://pith.science/pith/S46HULF6XG6S5IS3KCYXE3K3WM","download_json":"https://pith.science/pith/S46HULF6XG6S5IS3KCYXE3K3WM.json","view_paper":"https://pith.science/paper/S46HULF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05867&json=true","fetch_graph":"https://pith.science/api/pith-number/S46HULF6XG6S5IS3KCYXE3K3WM/graph.json","fetch_events":"https://pith.science/api/pith-number/S46HULF6XG6S5IS3KCYXE3K3WM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S46HULF6XG6S5IS3KCYXE3K3WM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S46HULF6XG6S5IS3KCYXE3K3WM/action/storage_attestation","attest_author":"https://pith.science/pith/S46HULF6XG6S5IS3KCYXE3K3WM/action/author_attestation","sign_citation":"https://pith.science/pith/S46HULF6XG6S5IS3KCYXE3K3WM/action/citation_signature","submit_replication":"https://pith.science/pith/S46HULF6XG6S5IS3KCYXE3K3WM/action/replication_record"}},"created_at":"2026-07-05T03:48:52.388146+00:00","updated_at":"2026-07-05T03:48:52.388146+00:00"}