{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ATCS2XF3SMK7ZM4ZBDKLZAO5SB","short_pith_number":"pith:ATCS2XF3","schema_version":"1.0","canonical_sha256":"04c52d5cbb9315fcb39908d4bc81dd9076b37a11617bb79dfa083b334d142c82","source":{"kind":"arxiv","id":"1902.10482","version":2},"attestation_state":"computed","paper":{"title":"Induction Networks for Few-Shot Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binhua Li, Jian Sun, Ping Jian, Ruiying Geng, Xiaodan Zhu, Yongbin Li","submitted_at":"2019-02-27T12:16:55Z","abstract_excerpt":"Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared to a small support set at the sample-wise level. However, this sample-wise comparison may be severely disturbed by the various expressions in the same class. Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries. In this paper, we propose a novel Induction Network to learn such a g"},"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":"1902.10482","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T12:16:55Z","cross_cats_sorted":[],"title_canon_sha256":"0cd99aa09276e37407253bb848fdabde59413feab6211ce414052ceab315f12b","abstract_canon_sha256":"5afbfb2933c7de0910d57202089c27122ef5a2d9b7e8f0a3bf68d5ec9d760d87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:44.878602Z","signature_b64":"g3Tp6PVGNOwl8TQOHyfGUxJr3aEm/WycGbOVjq+8F45rQ+ItzRiX4ypKsZfPGpCjgokdIC4CqPptSyEEgB+IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04c52d5cbb9315fcb39908d4bc81dd9076b37a11617bb79dfa083b334d142c82","last_reissued_at":"2026-07-05T00:07:44.878231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:44.878231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Induction Networks for Few-Shot Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binhua Li, Jian Sun, Ping Jian, Ruiying Geng, Xiaodan Zhu, Yongbin Li","submitted_at":"2019-02-27T12:16:55Z","abstract_excerpt":"Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared to a small support set at the sample-wise level. However, this sample-wise comparison may be severely disturbed by the various expressions in the same class. Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries. In this paper, we propose a novel Induction Network to learn such a g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10482","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/1902.10482/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":"1902.10482","created_at":"2026-07-05T00:07:44.878285+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10482v2","created_at":"2026-07-05T00:07:44.878285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10482","created_at":"2026-07-05T00:07:44.878285+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATCS2XF3SMK7","created_at":"2026-07-05T00:07:44.878285+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATCS2XF3SMK7ZM4Z","created_at":"2026-07-05T00:07:44.878285+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATCS2XF3","created_at":"2026-07-05T00:07:44.878285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.06039","citing_title":"Few-shot Text Classification with Distributional Signatures","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATCS2XF3SMK7ZM4ZBDKLZAO5SB","json":"https://pith.science/pith/ATCS2XF3SMK7ZM4ZBDKLZAO5SB.json","graph_json":"https://pith.science/api/pith-number/ATCS2XF3SMK7ZM4ZBDKLZAO5SB/graph.json","events_json":"https://pith.science/api/pith-number/ATCS2XF3SMK7ZM4ZBDKLZAO5SB/events.json","paper":"https://pith.science/paper/ATCS2XF3"},"agent_actions":{"view_html":"https://pith.science/pith/ATCS2XF3SMK7ZM4ZBDKLZAO5SB","download_json":"https://pith.science/pith/ATCS2XF3SMK7ZM4ZBDKLZAO5SB.json","view_paper":"https://pith.science/paper/ATCS2XF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10482&json=true","fetch_graph":"https://pith.science/api/pith-number/ATCS2XF3SMK7ZM4ZBDKLZAO5SB/graph.json","fetch_events":"https://pith.science/api/pith-number/ATCS2XF3SMK7ZM4ZBDKLZAO5SB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATCS2XF3SMK7ZM4ZBDKLZAO5SB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATCS2XF3SMK7ZM4ZBDKLZAO5SB/action/storage_attestation","attest_author":"https://pith.science/pith/ATCS2XF3SMK7ZM4ZBDKLZAO5SB/action/author_attestation","sign_citation":"https://pith.science/pith/ATCS2XF3SMK7ZM4ZBDKLZAO5SB/action/citation_signature","submit_replication":"https://pith.science/pith/ATCS2XF3SMK7ZM4ZBDKLZAO5SB/action/replication_record"}},"created_at":"2026-07-05T00:07:44.878285+00:00","updated_at":"2026-07-05T00:07:44.878285+00:00"}