{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:STDINY5C2L72CPVJPH5N4GCSHY","short_pith_number":"pith:STDINY5C","schema_version":"1.0","canonical_sha256":"94c686e3a2d2ffa13ea979fade18523e33ae1450839a3e9897a3a2d80dd6c46a","source":{"kind":"arxiv","id":"1906.01819","version":1},"attestation_state":"computed","paper":{"title":"Discriminative Few-Shot Learning Based on Directional Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong-Yeon Cho, Jiwon Kim, Junyoung Park, Subin Yi, Yongseok Choi","submitted_at":"2019-06-05T04:34:10Z","abstract_excerpt":"Metric-based few-shot learning methods try to overcome the difficulty due to the lack of training examples by learning embedding to make comparison easy. We propose a novel algorithm to generate class representatives for few-shot classification tasks. As a probabilistic model for learned features of inputs, we consider a mixture of von Mises-Fisher distributions which is known to be more expressive than Gaussian in a high dimensional space. Then, from a discriminative classifier perspective, we get a better class representative considering inter-class correlation which has not been addressed b"},"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":"1906.01819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T04:34:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5825df4c0c95cd3f7092e9ee0384f15e150153b1d961fd48e6eed8a5fae8368c","abstract_canon_sha256":"44ab8a2046beb2af9eac45db0cd1e0ca1804140b5ceeab74e8fd7f63de72be5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:06.139843Z","signature_b64":"IoOHbUDcAeVOW8fx1AdiZotgeBsI7y+U8d6QoJ+NF8YKNbcsFakJQjiUF2klX2Siab2lObPYyf1BuVmkBCHaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94c686e3a2d2ffa13ea979fade18523e33ae1450839a3e9897a3a2d80dd6c46a","last_reissued_at":"2026-05-17T23:44:06.139135Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:06.139135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discriminative Few-Shot Learning Based on Directional Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong-Yeon Cho, Jiwon Kim, Junyoung Park, Subin Yi, Yongseok Choi","submitted_at":"2019-06-05T04:34:10Z","abstract_excerpt":"Metric-based few-shot learning methods try to overcome the difficulty due to the lack of training examples by learning embedding to make comparison easy. We propose a novel algorithm to generate class representatives for few-shot classification tasks. As a probabilistic model for learned features of inputs, we consider a mixture of von Mises-Fisher distributions which is known to be more expressive than Gaussian in a high dimensional space. Then, from a discriminative classifier perspective, we get a better class representative considering inter-class correlation which has not been addressed b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01819","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":"1906.01819","created_at":"2026-05-17T23:44:06.139248+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01819v1","created_at":"2026-05-17T23:44:06.139248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01819","created_at":"2026-05-17T23:44:06.139248+00:00"},{"alias_kind":"pith_short_12","alias_value":"STDINY5C2L72","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"STDINY5C2L72CPVJ","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"STDINY5C","created_at":"2026-05-18T12:33:27.125529+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/STDINY5C2L72CPVJPH5N4GCSHY","json":"https://pith.science/pith/STDINY5C2L72CPVJPH5N4GCSHY.json","graph_json":"https://pith.science/api/pith-number/STDINY5C2L72CPVJPH5N4GCSHY/graph.json","events_json":"https://pith.science/api/pith-number/STDINY5C2L72CPVJPH5N4GCSHY/events.json","paper":"https://pith.science/paper/STDINY5C"},"agent_actions":{"view_html":"https://pith.science/pith/STDINY5C2L72CPVJPH5N4GCSHY","download_json":"https://pith.science/pith/STDINY5C2L72CPVJPH5N4GCSHY.json","view_paper":"https://pith.science/paper/STDINY5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01819&json=true","fetch_graph":"https://pith.science/api/pith-number/STDINY5C2L72CPVJPH5N4GCSHY/graph.json","fetch_events":"https://pith.science/api/pith-number/STDINY5C2L72CPVJPH5N4GCSHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STDINY5C2L72CPVJPH5N4GCSHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STDINY5C2L72CPVJPH5N4GCSHY/action/storage_attestation","attest_author":"https://pith.science/pith/STDINY5C2L72CPVJPH5N4GCSHY/action/author_attestation","sign_citation":"https://pith.science/pith/STDINY5C2L72CPVJPH5N4GCSHY/action/citation_signature","submit_replication":"https://pith.science/pith/STDINY5C2L72CPVJPH5N4GCSHY/action/replication_record"}},"created_at":"2026-05-17T23:44:06.139248+00:00","updated_at":"2026-05-17T23:44:06.139248+00:00"}