{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KJCB5UIZVDFMIYBMQHNGXFI6D4","short_pith_number":"pith:KJCB5UIZ","schema_version":"1.0","canonical_sha256":"52441ed119a8cac4602c81da6b951e1f0e123eebe7c4b8a53136fc49d9d8ab7b","source":{"kind":"arxiv","id":"1905.08845","version":2},"attestation_state":"computed","paper":{"title":"Semi-Supervised Learning with Scarce Annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Kai Han, Sebastien Ehrhardt, Sylvestre-Alvise Rebuffi","submitted_at":"2019-05-21T19:41:42Z","abstract_excerpt":"While semi-supervised learning (SSL) algorithms provide an efficient way to make use of both labelled and unlabelled data, they generally struggle when the number of annotated samples is very small. In this work, we consider the problem of SSL multi-class classification with very few labelled instances. We introduce two key ideas. The first is a simple but effective one: we leverage the power of transfer learning among different tasks and self-supervision to initialize a good representation of the data without making use of any label. The second idea is a new algorithm for SSL that can exploit"},"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":"1905.08845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-21T19:41:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5a04f5c7062b61eef21b9ab62d5ad6d19898612344e89ef64855ec03b4cda7bb","abstract_canon_sha256":"f616d026c8667bcd0f1dc30590044e9367f5feac1cef587ab3ebb2ef7d8ca317"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:22.847644Z","signature_b64":"AoAAxX4j/b9OrTFx4m2Sd3hQdoxHBiFuGpeP4M+EZ1JmdGzMgLWlE9sFKsdIVAlU2ujHUtXm4+gQ0v5ZdhNkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52441ed119a8cac4602c81da6b951e1f0e123eebe7c4b8a53136fc49d9d8ab7b","last_reissued_at":"2026-07-05T00:57:22.847252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:22.847252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Learning with Scarce Annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Kai Han, Sebastien Ehrhardt, Sylvestre-Alvise Rebuffi","submitted_at":"2019-05-21T19:41:42Z","abstract_excerpt":"While semi-supervised learning (SSL) algorithms provide an efficient way to make use of both labelled and unlabelled data, they generally struggle when the number of annotated samples is very small. In this work, we consider the problem of SSL multi-class classification with very few labelled instances. We introduce two key ideas. The first is a simple but effective one: we leverage the power of transfer learning among different tasks and self-supervision to initialize a good representation of the data without making use of any label. The second idea is a new algorithm for SSL that can exploit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08845","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/1905.08845/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":"1905.08845","created_at":"2026-07-05T00:57:22.847321+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.08845v2","created_at":"2026-07-05T00:57:22.847321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08845","created_at":"2026-07-05T00:57:22.847321+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJCB5UIZVDFM","created_at":"2026-07-05T00:57:22.847321+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJCB5UIZVDFMIYBM","created_at":"2026-07-05T00:57:22.847321+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJCB5UIZ","created_at":"2026-07-05T00:57:22.847321+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/KJCB5UIZVDFMIYBMQHNGXFI6D4","json":"https://pith.science/pith/KJCB5UIZVDFMIYBMQHNGXFI6D4.json","graph_json":"https://pith.science/api/pith-number/KJCB5UIZVDFMIYBMQHNGXFI6D4/graph.json","events_json":"https://pith.science/api/pith-number/KJCB5UIZVDFMIYBMQHNGXFI6D4/events.json","paper":"https://pith.science/paper/KJCB5UIZ"},"agent_actions":{"view_html":"https://pith.science/pith/KJCB5UIZVDFMIYBMQHNGXFI6D4","download_json":"https://pith.science/pith/KJCB5UIZVDFMIYBMQHNGXFI6D4.json","view_paper":"https://pith.science/paper/KJCB5UIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.08845&json=true","fetch_graph":"https://pith.science/api/pith-number/KJCB5UIZVDFMIYBMQHNGXFI6D4/graph.json","fetch_events":"https://pith.science/api/pith-number/KJCB5UIZVDFMIYBMQHNGXFI6D4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJCB5UIZVDFMIYBMQHNGXFI6D4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJCB5UIZVDFMIYBMQHNGXFI6D4/action/storage_attestation","attest_author":"https://pith.science/pith/KJCB5UIZVDFMIYBMQHNGXFI6D4/action/author_attestation","sign_citation":"https://pith.science/pith/KJCB5UIZVDFMIYBMQHNGXFI6D4/action/citation_signature","submit_replication":"https://pith.science/pith/KJCB5UIZVDFMIYBMQHNGXFI6D4/action/replication_record"}},"created_at":"2026-07-05T00:57:22.847321+00:00","updated_at":"2026-07-05T00:57:22.847321+00:00"}