{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:L6TZK3WEYIEEYL3XH7RYO4OWQ7","short_pith_number":"pith:L6TZK3WE","schema_version":"1.0","canonical_sha256":"5fa7956ec4c2084c2f773fe38771d687c053140a847216984e25ce18f2c7324d","source":{"kind":"arxiv","id":"1807.05076","version":1},"attestation_state":"computed","paper":{"title":"Metalearning with Hebbian Fast Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Adam Trischler, Tsendsuren Munkhdalai","submitted_at":"2018-07-12T14:40:06Z","abstract_excerpt":"We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a single shot. It builds representations via slow weights, learned across tasks through SGD, while fast weights constructed by a Hebbian learning rule implement one-shot binding for each new task. On the Omniglot, Mini-ImageNet, and Penn Treebank one-shot learning benchmarks, our model achieves state-of-the-art results."},"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":"1807.05076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-07-12T14:40:06Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"9fed20da3127fdc7c7b5d71509b6ae9a6c35aff951c7640e75faa1530373077e","abstract_canon_sha256":"9c76d9159d124c8cffc8d7cab9f1cca27a3762fdfe69052c930c96e7a96d8bc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:49.061463Z","signature_b64":"VLmlakzGtWEnFZrfs3Ef6mqyCdPxsB7auI7Zt+ntlEr12wb00a+ALLV0XjvK0bb5IFR9JDRZlTXNwgV1HLIuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fa7956ec4c2084c2f773fe38771d687c053140a847216984e25ce18f2c7324d","last_reissued_at":"2026-05-18T00:10:49.060968Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:49.060968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metalearning with Hebbian Fast Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Adam Trischler, Tsendsuren Munkhdalai","submitted_at":"2018-07-12T14:40:06Z","abstract_excerpt":"We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a single shot. It builds representations via slow weights, learned across tasks through SGD, while fast weights constructed by a Hebbian learning rule implement one-shot binding for each new task. On the Omniglot, Mini-ImageNet, and Penn Treebank one-shot learning benchmarks, our model achieves state-of-the-art results."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05076","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":"1807.05076","created_at":"2026-05-18T00:10:49.061040+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.05076v1","created_at":"2026-05-18T00:10:49.061040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05076","created_at":"2026-05-18T00:10:49.061040+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6TZK3WEYIEE","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6TZK3WEYIEEYL3X","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6TZK3WE","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.26692","citing_title":"Kimi Linear: An Expressive, Efficient Attention Architecture","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02920","citing_title":"Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6TZK3WEYIEEYL3XH7RYO4OWQ7","json":"https://pith.science/pith/L6TZK3WEYIEEYL3XH7RYO4OWQ7.json","graph_json":"https://pith.science/api/pith-number/L6TZK3WEYIEEYL3XH7RYO4OWQ7/graph.json","events_json":"https://pith.science/api/pith-number/L6TZK3WEYIEEYL3XH7RYO4OWQ7/events.json","paper":"https://pith.science/paper/L6TZK3WE"},"agent_actions":{"view_html":"https://pith.science/pith/L6TZK3WEYIEEYL3XH7RYO4OWQ7","download_json":"https://pith.science/pith/L6TZK3WEYIEEYL3XH7RYO4OWQ7.json","view_paper":"https://pith.science/paper/L6TZK3WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.05076&json=true","fetch_graph":"https://pith.science/api/pith-number/L6TZK3WEYIEEYL3XH7RYO4OWQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/L6TZK3WEYIEEYL3XH7RYO4OWQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6TZK3WEYIEEYL3XH7RYO4OWQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6TZK3WEYIEEYL3XH7RYO4OWQ7/action/storage_attestation","attest_author":"https://pith.science/pith/L6TZK3WEYIEEYL3XH7RYO4OWQ7/action/author_attestation","sign_citation":"https://pith.science/pith/L6TZK3WEYIEEYL3XH7RYO4OWQ7/action/citation_signature","submit_replication":"https://pith.science/pith/L6TZK3WEYIEEYL3XH7RYO4OWQ7/action/replication_record"}},"created_at":"2026-05-18T00:10:49.061040+00:00","updated_at":"2026-05-18T00:10:49.061040+00:00"}