{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VFVFCQESEZZNSI2EGNORGDZB7F","short_pith_number":"pith:VFVFCQES","canonical_record":{"source":{"id":"1806.00852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-03T19:16:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fb8f81b9f564b645dad2b3df93572433759c91adbd1ac12d5c7b740d28339287","abstract_canon_sha256":"4fc939d87ceeaacdcfcfe1fab3573aea42f9bc20c5b40819d75acf5df326df22"},"schema_version":"1.0"},"canonical_sha256":"a96a5140922672d92344335d130f21f968c38f0ca505e4a360535ffadd5d2d54","source":{"kind":"arxiv","id":"1806.00852","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00852","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00852v1","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00852","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"pith_short_12","alias_value":"VFVFCQESEZZN","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VFVFCQESEZZNSI2E","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VFVFCQES","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VFVFCQESEZZNSI2EGNORGDZB7F","target":"record","payload":{"canonical_record":{"source":{"id":"1806.00852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-03T19:16:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fb8f81b9f564b645dad2b3df93572433759c91adbd1ac12d5c7b740d28339287","abstract_canon_sha256":"4fc939d87ceeaacdcfcfe1fab3573aea42f9bc20c5b40819d75acf5df326df22"},"schema_version":"1.0"},"canonical_sha256":"a96a5140922672d92344335d130f21f968c38f0ca505e4a360535ffadd5d2d54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:18.216796Z","signature_b64":"SblBVXhvsKw1JX1+9uls01noQDh30t7lvsO8Ife/tDrLzys7hhuwFlwMLL9kppK8SqzwWjY2uatXz4bIGobqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a96a5140922672d92344335d130f21f968c38f0ca505e4a360535ffadd5d2d54","last_reissued_at":"2026-05-18T00:14:18.216155Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:18.216155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.00852","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nc5I0RZXQEu5hj/JKEsrwbqNu7CyVCV3irZsIkBm25twcH6+Pc7tML7G9OAZzBcyp3GIsPMjbvWJc6cPWLr7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:23:35.096815Z"},"content_sha256":"8056b52dff578ba47e3d76ef6c5d46dc90a8505d86572252ccfce5b6c092c18f","schema_version":"1.0","event_id":"sha256:8056b52dff578ba47e3d76ef6c5d46dc90a8505d86572252ccfce5b6c092c18f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VFVFCQESEZZNSI2EGNORGDZB7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Importance of Attention in Meta-Learning for Few-Shot Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Jesson, Gabriel Chartrand, Hassan Chouaib, Mohammad Havaei, Nicolas Chapados, Stan Matwin, Thomas Vincent, Xiang Jiang","submitted_at":"2018-06-03T19:16:50Z","abstract_excerpt":"Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the knowledge learned across many tasks as an inductive bias towards better natural language understanding. Based on the Model-Agnostic Meta-Learning framework (MAML), we introduce the Attentive Task-Agnostic Meta-Learning (ATAML) algorithm for text classification. The essential difference between MAML and ATAML is in the separation of task-agnostic representation lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00852","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+E3wfgXpr4GFjhIO7uOQV5rseOq0XzCzdo0Pb5x3y8uapbRhVxu1U6rZ5Jq9Akj6TzOBMPFunAuik/5HSTbsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:23:35.097545Z"},"content_sha256":"b54552d5e99ea2e3e86cb4e577629e02a2d503fc1578c9eb339d92a9eadc31d4","schema_version":"1.0","event_id":"sha256:b54552d5e99ea2e3e86cb4e577629e02a2d503fc1578c9eb339d92a9eadc31d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFVFCQESEZZNSI2EGNORGDZB7F/bundle.json","state_url":"https://pith.science/pith/VFVFCQESEZZNSI2EGNORGDZB7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFVFCQESEZZNSI2EGNORGDZB7F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T10:23:35Z","links":{"resolver":"https://pith.science/pith/VFVFCQESEZZNSI2EGNORGDZB7F","bundle":"https://pith.science/pith/VFVFCQESEZZNSI2EGNORGDZB7F/bundle.json","state":"https://pith.science/pith/VFVFCQESEZZNSI2EGNORGDZB7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFVFCQESEZZNSI2EGNORGDZB7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VFVFCQESEZZNSI2EGNORGDZB7F","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4fc939d87ceeaacdcfcfe1fab3573aea42f9bc20c5b40819d75acf5df326df22","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-03T19:16:50Z","title_canon_sha256":"fb8f81b9f564b645dad2b3df93572433759c91adbd1ac12d5c7b740d28339287"},"schema_version":"1.0","source":{"id":"1806.00852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00852","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00852v1","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00852","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"pith_short_12","alias_value":"VFVFCQESEZZN","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VFVFCQESEZZNSI2E","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VFVFCQES","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:b54552d5e99ea2e3e86cb4e577629e02a2d503fc1578c9eb339d92a9eadc31d4","target":"graph","created_at":"2026-05-18T00:14:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the knowledge learned across many tasks as an inductive bias towards better natural language understanding. Based on the Model-Agnostic Meta-Learning framework (MAML), we introduce the Attentive Task-Agnostic Meta-Learning (ATAML) algorithm for text classification. The essential difference between MAML and ATAML is in the separation of task-agnostic representation lear","authors_text":"Andrew Jesson, Gabriel Chartrand, Hassan Chouaib, Mohammad Havaei, Nicolas Chapados, Stan Matwin, Thomas Vincent, Xiang Jiang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-03T19:16:50Z","title":"On the Importance of Attention in Meta-Learning for Few-Shot Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00852","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8056b52dff578ba47e3d76ef6c5d46dc90a8505d86572252ccfce5b6c092c18f","target":"record","created_at":"2026-05-18T00:14:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4fc939d87ceeaacdcfcfe1fab3573aea42f9bc20c5b40819d75acf5df326df22","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-03T19:16:50Z","title_canon_sha256":"fb8f81b9f564b645dad2b3df93572433759c91adbd1ac12d5c7b740d28339287"},"schema_version":"1.0","source":{"id":"1806.00852","kind":"arxiv","version":1}},"canonical_sha256":"a96a5140922672d92344335d130f21f968c38f0ca505e4a360535ffadd5d2d54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a96a5140922672d92344335d130f21f968c38f0ca505e4a360535ffadd5d2d54","first_computed_at":"2026-05-18T00:14:18.216155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:18.216155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SblBVXhvsKw1JX1+9uls01noQDh30t7lvsO8Ife/tDrLzys7hhuwFlwMLL9kppK8SqzwWjY2uatXz4bIGobqBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:18.216796Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.00852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8056b52dff578ba47e3d76ef6c5d46dc90a8505d86572252ccfce5b6c092c18f","sha256:b54552d5e99ea2e3e86cb4e577629e02a2d503fc1578c9eb339d92a9eadc31d4"],"state_sha256":"61850b24a648b8d8b54310901d92ce82d92c26790eff30f1c8af6c2a7c58329c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BehPMjFJs7FYR2aUqjQHuJqxIJvOmP+cFf0+UeiFaaDZsUceKVHjIn64YZR49F0isbnS1E/TqY+hbe7QDHiLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:23:35.101269Z","bundle_sha256":"c32178a56b55577cf1cb609c0fe49bb05707a6fea3ca55227ad6dbf10840de6e"}}