{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IUI3YE6TKCWDTDPGIBE7KGOLGS","short_pith_number":"pith:IUI3YE6T","schema_version":"1.0","canonical_sha256":"4511bc13d350ac398de64049f519cb3483517534683f0bc4973c19aadfee7805","source":{"kind":"arxiv","id":"1703.00767","version":3},"attestation_state":"computed","paper":{"title":"Attentive Recurrent Comparators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ambedkar Dukkipati, Pranav Shyam, Shubham Gupta","submitted_at":"2017-03-02T12:47:40Z","abstract_excerpt":"Rapid learning requires flexible representations to quickly adopt to new evidence. We develop a novel class of models called Attentive Recurrent Comparators (ARCs) that form representations of objects by cycling through them and making observations. Using the representations extracted by ARCs, we develop a way of approximating a \\textit{dynamic representation space} and use it for one-shot learning. In the task of one-shot classification on the Omniglot dataset, we achieve the state of the art performance with an error rate of 1.5\\%. This represents the first super-human result achieved for th"},"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":"1703.00767","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-02T12:47:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"835f730b59aeb9b21f9dc354567e9d6175d249fce6642a50bc867ddafed3f569","abstract_canon_sha256":"b686980c1b71e54f8ddc3e0ab245a15c648761de0683f6b921295ee9d504f37c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:12.455249Z","signature_b64":"pwExZlP43khY1lYW6pGJTg8R7ekjePWaM5yptMt1tXwACS9O9ZpJD8TalFREQcX3qFTs94T7zk7Qz0BXWtS9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4511bc13d350ac398de64049f519cb3483517534683f0bc4973c19aadfee7805","last_reissued_at":"2026-05-18T00:41:12.454537Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:12.454537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attentive Recurrent Comparators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ambedkar Dukkipati, Pranav Shyam, Shubham Gupta","submitted_at":"2017-03-02T12:47:40Z","abstract_excerpt":"Rapid learning requires flexible representations to quickly adopt to new evidence. We develop a novel class of models called Attentive Recurrent Comparators (ARCs) that form representations of objects by cycling through them and making observations. Using the representations extracted by ARCs, we develop a way of approximating a \\textit{dynamic representation space} and use it for one-shot learning. In the task of one-shot classification on the Omniglot dataset, we achieve the state of the art performance with an error rate of 1.5\\%. This represents the first super-human result achieved for th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00767","kind":"arxiv","version":3},"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":"1703.00767","created_at":"2026-05-18T00:41:12.454644+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00767v3","created_at":"2026-05-18T00:41:12.454644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00767","created_at":"2026-05-18T00:41:12.454644+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUI3YE6TKCWD","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUI3YE6TKCWDTDPG","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUI3YE6T","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1911.05507","citing_title":"Compressive Transformers for Long-Range Sequence Modelling","ref_index":89,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUI3YE6TKCWDTDPGIBE7KGOLGS","json":"https://pith.science/pith/IUI3YE6TKCWDTDPGIBE7KGOLGS.json","graph_json":"https://pith.science/api/pith-number/IUI3YE6TKCWDTDPGIBE7KGOLGS/graph.json","events_json":"https://pith.science/api/pith-number/IUI3YE6TKCWDTDPGIBE7KGOLGS/events.json","paper":"https://pith.science/paper/IUI3YE6T"},"agent_actions":{"view_html":"https://pith.science/pith/IUI3YE6TKCWDTDPGIBE7KGOLGS","download_json":"https://pith.science/pith/IUI3YE6TKCWDTDPGIBE7KGOLGS.json","view_paper":"https://pith.science/paper/IUI3YE6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00767&json=true","fetch_graph":"https://pith.science/api/pith-number/IUI3YE6TKCWDTDPGIBE7KGOLGS/graph.json","fetch_events":"https://pith.science/api/pith-number/IUI3YE6TKCWDTDPGIBE7KGOLGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUI3YE6TKCWDTDPGIBE7KGOLGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUI3YE6TKCWDTDPGIBE7KGOLGS/action/storage_attestation","attest_author":"https://pith.science/pith/IUI3YE6TKCWDTDPGIBE7KGOLGS/action/author_attestation","sign_citation":"https://pith.science/pith/IUI3YE6TKCWDTDPGIBE7KGOLGS/action/citation_signature","submit_replication":"https://pith.science/pith/IUI3YE6TKCWDTDPGIBE7KGOLGS/action/replication_record"}},"created_at":"2026-05-18T00:41:12.454644+00:00","updated_at":"2026-05-18T00:41:12.454644+00:00"}