{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7C3D2NMNSBYQUOOC2TMOO7W3P5","short_pith_number":"pith:7C3D2NMN","canonical_record":{"source":{"id":"1810.09502","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-22T18:48:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bf65fa99c6df08261178943f441cd323b5590cadaba7be1e469fdbd023210c72","abstract_canon_sha256":"20ac87a491a8e7ddc648c0d4712ae887aacf436e9cc09c252a3acf2aefc3c97d"},"schema_version":"1.0"},"canonical_sha256":"f8b63d358d90710a39c2d4d8e77edb7f4a264d3a5ea79efa115513279458f2d9","source":{"kind":"arxiv","id":"1810.09502","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09502","created_at":"2026-05-17T23:51:58Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09502v3","created_at":"2026-05-17T23:51:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09502","created_at":"2026-05-17T23:51:58Z"},{"alias_kind":"pith_short_12","alias_value":"7C3D2NMNSBYQ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7C3D2NMNSBYQUOOC","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7C3D2NMN","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7C3D2NMNSBYQUOOC2TMOO7W3P5","target":"record","payload":{"canonical_record":{"source":{"id":"1810.09502","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-22T18:48:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bf65fa99c6df08261178943f441cd323b5590cadaba7be1e469fdbd023210c72","abstract_canon_sha256":"20ac87a491a8e7ddc648c0d4712ae887aacf436e9cc09c252a3acf2aefc3c97d"},"schema_version":"1.0"},"canonical_sha256":"f8b63d358d90710a39c2d4d8e77edb7f4a264d3a5ea79efa115513279458f2d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:58.825650Z","signature_b64":"DUVgVBLTuNreN4pYTYzIrlauCvVWe0IFvRv4fuEyYWSugheJK80YWvXYuXaXtT25WFc59Yot+T/JL9G/5GdYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8b63d358d90710a39c2d4d8e77edb7f4a264d3a5ea79efa115513279458f2d9","last_reissued_at":"2026-05-17T23:51:58.825207Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:58.825207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.09502","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a6Wx9IxZfGXxkKnyDYAfmkqZxdHnD8mcQck/rJH7g7nEjiKB5/HFCJXllDZIkUhPu2T3wT4tKgUWZR66VZOwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:43:13.103049Z"},"content_sha256":"ba31582fe77186417efcf1a22ac950fd29d9bb8da4f71ae2507774a5f87ac509","schema_version":"1.0","event_id":"sha256:ba31582fe77186417efcf1a22ac950fd29d9bb8da4f71ae2507774a5f87ac509"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7C3D2NMNSBYQUOOC2TMOO7W3P5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to train your MAML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amos Storkey, Antreas Antoniou, Harrison Edwards","submitted_at":"2018-10-22T18:48:16Z","abstract_excerpt":"The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic Meta Learning or MAML is currently one of the best approaches for few-shot learning via meta-learning. MAML is simple, elegant and very powerful, however, it has a variety of issues, such as being very sensitive to neural network architectures, often leading to instability during training, requiring arduous hyperparameter searches to stabilize training and achieve high generalization and being very computationally e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09502","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I0WzbXaqRxIx8UOefZoTe3tOsmyMA4RRDjJX42HRmmvRx9G8a4uGG66C/9P8DggZ6jJsWGXJaIqtzE3Jbkj7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:43:13.103460Z"},"content_sha256":"d83cd46765106feea4483eb0be102cc79557ae0562081d3a3199425778e8b125","schema_version":"1.0","event_id":"sha256:d83cd46765106feea4483eb0be102cc79557ae0562081d3a3199425778e8b125"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7C3D2NMNSBYQUOOC2TMOO7W3P5/bundle.json","state_url":"https://pith.science/pith/7C3D2NMNSBYQUOOC2TMOO7W3P5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7C3D2NMNSBYQUOOC2TMOO7W3P5/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":"2026-05-26T04:43:13Z","links":{"resolver":"https://pith.science/pith/7C3D2NMNSBYQUOOC2TMOO7W3P5","bundle":"https://pith.science/pith/7C3D2NMNSBYQUOOC2TMOO7W3P5/bundle.json","state":"https://pith.science/pith/7C3D2NMNSBYQUOOC2TMOO7W3P5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7C3D2NMNSBYQUOOC2TMOO7W3P5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7C3D2NMNSBYQUOOC2TMOO7W3P5","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":"20ac87a491a8e7ddc648c0d4712ae887aacf436e9cc09c252a3acf2aefc3c97d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-22T18:48:16Z","title_canon_sha256":"bf65fa99c6df08261178943f441cd323b5590cadaba7be1e469fdbd023210c72"},"schema_version":"1.0","source":{"id":"1810.09502","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09502","created_at":"2026-05-17T23:51:58Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09502v3","created_at":"2026-05-17T23:51:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09502","created_at":"2026-05-17T23:51:58Z"},{"alias_kind":"pith_short_12","alias_value":"7C3D2NMNSBYQ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7C3D2NMNSBYQUOOC","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7C3D2NMN","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:d83cd46765106feea4483eb0be102cc79557ae0562081d3a3199425778e8b125","target":"graph","created_at":"2026-05-17T23:51:58Z","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":"The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic Meta Learning or MAML is currently one of the best approaches for few-shot learning via meta-learning. MAML is simple, elegant and very powerful, however, it has a variety of issues, such as being very sensitive to neural network architectures, often leading to instability during training, requiring arduous hyperparameter searches to stabilize training and achieve high generalization and being very computationally e","authors_text":"Amos Storkey, Antreas Antoniou, Harrison Edwards","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-22T18:48:16Z","title":"How to train your MAML"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09502","kind":"arxiv","version":3},"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:ba31582fe77186417efcf1a22ac950fd29d9bb8da4f71ae2507774a5f87ac509","target":"record","created_at":"2026-05-17T23:51:58Z","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":"20ac87a491a8e7ddc648c0d4712ae887aacf436e9cc09c252a3acf2aefc3c97d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-22T18:48:16Z","title_canon_sha256":"bf65fa99c6df08261178943f441cd323b5590cadaba7be1e469fdbd023210c72"},"schema_version":"1.0","source":{"id":"1810.09502","kind":"arxiv","version":3}},"canonical_sha256":"f8b63d358d90710a39c2d4d8e77edb7f4a264d3a5ea79efa115513279458f2d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8b63d358d90710a39c2d4d8e77edb7f4a264d3a5ea79efa115513279458f2d9","first_computed_at":"2026-05-17T23:51:58.825207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:58.825207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DUVgVBLTuNreN4pYTYzIrlauCvVWe0IFvRv4fuEyYWSugheJK80YWvXYuXaXtT25WFc59Yot+T/JL9G/5GdYBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:58.825650Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.09502","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba31582fe77186417efcf1a22ac950fd29d9bb8da4f71ae2507774a5f87ac509","sha256:d83cd46765106feea4483eb0be102cc79557ae0562081d3a3199425778e8b125"],"state_sha256":"6872e781b271cc33f48fb9df12e390f3ebdde3099f243b7f9a4b511860afc459"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YccO0+3ZpAWD7fgqMtKdjs1LlY76jw2SZkAjvx/vSxn+vfY4cMBS7ASLDXXYFUXAqgE0vAJskuWEkOse2laUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T04:43:13.107409Z","bundle_sha256":"45a180b22d27cc2daa603c7f7147dca269556938379086d9148689875c5c5111"}}