{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5K7OL3U4PAAS5WXIXHI3N5LFQQ","short_pith_number":"pith:5K7OL3U4","schema_version":"1.0","canonical_sha256":"eabee5ee9c78012edae8b9d1b6f565841f2a91089dd868d10741a5e35b9579e5","source":{"kind":"arxiv","id":"1812.03664","version":6},"attestation_state":"computed","paper":{"title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Fei Sha, Han-Jia Ye, Hexiang Hu","submitted_at":"2018-12-10T07:55:56Z","abstract_excerpt":"Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set functio"},"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":"1812.03664","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-10T07:55:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"62c3ee3de3bf0cdb36e95c1173630e01f59a79c598ea36c740a4514231e02cce","abstract_canon_sha256":"960195f1d9e57f4c970a4fcbdb814b078f2333a71fcaecb11919855c9a02a581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:31.517807Z","signature_b64":"oIPstKYiqjAD/fyI5wdFuIYDqTIOyA6ikaY8ykUWT4897krwISnDmAR6CoWRx84ZXzIq9G1lmnc84FUb61PrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eabee5ee9c78012edae8b9d1b6f565841f2a91089dd868d10741a5e35b9579e5","last_reissued_at":"2026-07-05T02:48:31.517339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:31.517339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Fei Sha, Han-Jia Ye, Hexiang Hu","submitted_at":"2018-12-10T07:55:56Z","abstract_excerpt":"Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set functio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03664","kind":"arxiv","version":6},"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/1812.03664/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":"1812.03664","created_at":"2026-07-05T02:48:31.517398+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.03664v6","created_at":"2026-07-05T02:48:31.517398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03664","created_at":"2026-07-05T02:48:31.517398+00:00"},{"alias_kind":"pith_short_12","alias_value":"5K7OL3U4PAAS","created_at":"2026-07-05T02:48:31.517398+00:00"},{"alias_kind":"pith_short_16","alias_value":"5K7OL3U4PAAS5WXI","created_at":"2026-07-05T02:48:31.517398+00:00"},{"alias_kind":"pith_short_8","alias_value":"5K7OL3U4","created_at":"2026-07-05T02:48:31.517398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14145","citing_title":"Rethinking the Good Enough Embedding for Easy Few-Shot Learning","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5K7OL3U4PAAS5WXIXHI3N5LFQQ","json":"https://pith.science/pith/5K7OL3U4PAAS5WXIXHI3N5LFQQ.json","graph_json":"https://pith.science/api/pith-number/5K7OL3U4PAAS5WXIXHI3N5LFQQ/graph.json","events_json":"https://pith.science/api/pith-number/5K7OL3U4PAAS5WXIXHI3N5LFQQ/events.json","paper":"https://pith.science/paper/5K7OL3U4"},"agent_actions":{"view_html":"https://pith.science/pith/5K7OL3U4PAAS5WXIXHI3N5LFQQ","download_json":"https://pith.science/pith/5K7OL3U4PAAS5WXIXHI3N5LFQQ.json","view_paper":"https://pith.science/paper/5K7OL3U4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.03664&json=true","fetch_graph":"https://pith.science/api/pith-number/5K7OL3U4PAAS5WXIXHI3N5LFQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5K7OL3U4PAAS5WXIXHI3N5LFQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5K7OL3U4PAAS5WXIXHI3N5LFQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5K7OL3U4PAAS5WXIXHI3N5LFQQ/action/storage_attestation","attest_author":"https://pith.science/pith/5K7OL3U4PAAS5WXIXHI3N5LFQQ/action/author_attestation","sign_citation":"https://pith.science/pith/5K7OL3U4PAAS5WXIXHI3N5LFQQ/action/citation_signature","submit_replication":"https://pith.science/pith/5K7OL3U4PAAS5WXIXHI3N5LFQQ/action/replication_record"}},"created_at":"2026-07-05T02:48:31.517398+00:00","updated_at":"2026-07-05T02:48:31.517398+00:00"}