{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:N4EN526GWNKA3OAJEDRIL5QEXN","short_pith_number":"pith:N4EN526G","schema_version":"1.0","canonical_sha256":"6f08deebc6b3540db80920e285f604bb6955179d67b7f4ddc7185033f9272071","source":{"kind":"arxiv","id":"1802.04376","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Learning with Metric-Agnostic Conditional Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Art\\\"em Yankov, Courtney D. Corley, Lawrence Phillips, Nathan Hilliard, Nathan O. Hodas, Scott Howland","submitted_at":"2018-02-12T21:56:12Z","abstract_excerpt":"Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architecture where class representations are conditioned for each few-shot trial based on a target image. We also deviate from traditional metric-learning approaches by training a network to perform comparisons between classes rather than relying on a static metric comparison. This allows the network to decide what aspects of each class are important for the comparison at hand. We find that this flexible architecture works w"},"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":"1802.04376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T21:56:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7c14ed940d15d79d8bcd4a2539fc364ed751943261a52f9eee485772637f0a2e","abstract_canon_sha256":"2ed6b23acfac4b4a494b8a18c09987786e44f0d1e9fa03f9d0e8f821215531b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:44.352151Z","signature_b64":"fY4BkP5J9A7Bj5RFgy5+qFKLWVr/Ag3gtA4KaU+QdaP/rX/0WiIdnmVyz0qqBnA/YgvvIzaSRwNJTz69N7JkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f08deebc6b3540db80920e285f604bb6955179d67b7f4ddc7185033f9272071","last_reissued_at":"2026-05-18T00:23:44.351620Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:44.351620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Learning with Metric-Agnostic Conditional Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Art\\\"em Yankov, Courtney D. Corley, Lawrence Phillips, Nathan Hilliard, Nathan O. Hodas, Scott Howland","submitted_at":"2018-02-12T21:56:12Z","abstract_excerpt":"Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architecture where class representations are conditioned for each few-shot trial based on a target image. We also deviate from traditional metric-learning approaches by training a network to perform comparisons between classes rather than relying on a static metric comparison. This allows the network to decide what aspects of each class are important for the comparison at hand. We find that this flexible architecture works w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04376","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":""},"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":"1802.04376","created_at":"2026-05-18T00:23:44.351693+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04376v1","created_at":"2026-05-18T00:23:44.351693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04376","created_at":"2026-05-18T00:23:44.351693+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4EN526GWNKA","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4EN526GWNKA3OAJ","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4EN526G","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11052","citing_title":"Further advantages of data augmentation on convolutional neural networks","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4EN526GWNKA3OAJEDRIL5QEXN","json":"https://pith.science/pith/N4EN526GWNKA3OAJEDRIL5QEXN.json","graph_json":"https://pith.science/api/pith-number/N4EN526GWNKA3OAJEDRIL5QEXN/graph.json","events_json":"https://pith.science/api/pith-number/N4EN526GWNKA3OAJEDRIL5QEXN/events.json","paper":"https://pith.science/paper/N4EN526G"},"agent_actions":{"view_html":"https://pith.science/pith/N4EN526GWNKA3OAJEDRIL5QEXN","download_json":"https://pith.science/pith/N4EN526GWNKA3OAJEDRIL5QEXN.json","view_paper":"https://pith.science/paper/N4EN526G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04376&json=true","fetch_graph":"https://pith.science/api/pith-number/N4EN526GWNKA3OAJEDRIL5QEXN/graph.json","fetch_events":"https://pith.science/api/pith-number/N4EN526GWNKA3OAJEDRIL5QEXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4EN526GWNKA3OAJEDRIL5QEXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4EN526GWNKA3OAJEDRIL5QEXN/action/storage_attestation","attest_author":"https://pith.science/pith/N4EN526GWNKA3OAJEDRIL5QEXN/action/author_attestation","sign_citation":"https://pith.science/pith/N4EN526GWNKA3OAJEDRIL5QEXN/action/citation_signature","submit_replication":"https://pith.science/pith/N4EN526GWNKA3OAJEDRIL5QEXN/action/replication_record"}},"created_at":"2026-05-18T00:23:44.351693+00:00","updated_at":"2026-05-18T00:23:44.351693+00:00"}