{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2C7VZB7PN4ADGFLTSLEBGFMZED","short_pith_number":"pith:2C7VZB7P","canonical_record":{"source":{"id":"1902.03356","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-09T02:34:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"14a2e74da616a7a621a6ee301a255c8907d6e34f7c74ca13472c950c8079a969","abstract_canon_sha256":"70755639f9f8950a48116cbb9a269b416a231028c7e97159a4c8422b3b19a759"},"schema_version":"1.0"},"canonical_sha256":"d0bf5c87ef6f0033157392c813159920db23603169a30ff43f2e6e4d01323f50","source":{"kind":"arxiv","id":"1902.03356","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.03356","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"arxiv_version","alias_value":"1902.03356v3","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03356","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"pith_short_12","alias_value":"2C7VZB7PN4AD","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"pith_short_16","alias_value":"2C7VZB7PN4ADGFLT","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"pith_short_8","alias_value":"2C7VZB7P","created_at":"2026-07-05T00:32:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2C7VZB7PN4ADGFLTSLEBGFMZED","target":"record","payload":{"canonical_record":{"source":{"id":"1902.03356","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-09T02:34:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"14a2e74da616a7a621a6ee301a255c8907d6e34f7c74ca13472c950c8079a969","abstract_canon_sha256":"70755639f9f8950a48116cbb9a269b416a231028c7e97159a4c8422b3b19a759"},"schema_version":"1.0"},"canonical_sha256":"d0bf5c87ef6f0033157392c813159920db23603169a30ff43f2e6e4d01323f50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:20.973541Z","signature_b64":"4Jf5y8c8dFAiVYXmL0AGlF2S8VgLujJMVQQNVjZnwzcGTQLMO0iIu0wKx95DpAQNfmSiddiWro3hYRIIjoj/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0bf5c87ef6f0033157392c813159920db23603169a30ff43f2e6e4d01323f50","last_reissued_at":"2026-07-05T00:32:20.973060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:20.973060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.03356","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":"2026-07-05T00:32:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AoEyqFJ915dJxJ6keh8IYUcbfRq/6fcKDHGpxE5FVZNHFQ0X53M8t7b39Km+rmVJHk3sGCq69emiCx9FpW9RDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T06:44:02.944119Z"},"content_sha256":"1e6b1047b64cbdb6aeab6b5ce169d4ff1d2caa0a6bcc07c903797509a100c754","schema_version":"1.0","event_id":"sha256:1e6b1047b64cbdb6aeab6b5ce169d4ff1d2caa0a6bcc07c903797509a100c754"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2C7VZB7PN4ADGFLTSLEBGFMZED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Curvature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eunbyung Park, Junier B. Oliva","submitted_at":"2019-02-09T02:34:53Z","abstract_excerpt":"We propose meta-curvature (MC), a framework to learn curvature information for better generalization and fast model adaptation. MC expands on the model-agnostic meta-learner (MAML) by learning to transform the gradients in the inner optimization such that the transformed gradients achieve better generalization performance to a new task. For training large scale neural networks, we decompose the curvature matrix into smaller matrices in a novel scheme where we capture the dependencies of the model's parameters with a series of tensor products. We demonstrate the effects of our proposed method o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03356","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1902.03356/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:32:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vhs8QSvu7GgJvKnK0tKl4mJQob43tDzpL1jvyJKw9o77mHj/bE4rKtZRtoRV/uzTGLlq9R2u0G13v60h4spaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T06:44:02.944624Z"},"content_sha256":"7c095d739d40cf1ac97e5053201780dd2d4e478cbf16fe2282c43c150eba315a","schema_version":"1.0","event_id":"sha256:7c095d739d40cf1ac97e5053201780dd2d4e478cbf16fe2282c43c150eba315a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2C7VZB7PN4ADGFLTSLEBGFMZED/bundle.json","state_url":"https://pith.science/pith/2C7VZB7PN4ADGFLTSLEBGFMZED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2C7VZB7PN4ADGFLTSLEBGFMZED/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":"2026-08-22T06:44:02Z","links":{"resolver":"https://pith.science/pith/2C7VZB7PN4ADGFLTSLEBGFMZED","bundle":"https://pith.science/pith/2C7VZB7PN4ADGFLTSLEBGFMZED/bundle.json","state":"https://pith.science/pith/2C7VZB7PN4ADGFLTSLEBGFMZED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2C7VZB7PN4ADGFLTSLEBGFMZED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2C7VZB7PN4ADGFLTSLEBGFMZED","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":"70755639f9f8950a48116cbb9a269b416a231028c7e97159a4c8422b3b19a759","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-09T02:34:53Z","title_canon_sha256":"14a2e74da616a7a621a6ee301a255c8907d6e34f7c74ca13472c950c8079a969"},"schema_version":"1.0","source":{"id":"1902.03356","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.03356","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"arxiv_version","alias_value":"1902.03356v3","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03356","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"pith_short_12","alias_value":"2C7VZB7PN4AD","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"pith_short_16","alias_value":"2C7VZB7PN4ADGFLT","created_at":"2026-07-05T00:32:20Z"},{"alias_kind":"pith_short_8","alias_value":"2C7VZB7P","created_at":"2026-07-05T00:32:20Z"}],"graph_snapshots":[{"event_id":"sha256:7c095d739d40cf1ac97e5053201780dd2d4e478cbf16fe2282c43c150eba315a","target":"graph","created_at":"2026-07-05T00:32:20Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1902.03356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose meta-curvature (MC), a framework to learn curvature information for better generalization and fast model adaptation. MC expands on the model-agnostic meta-learner (MAML) by learning to transform the gradients in the inner optimization such that the transformed gradients achieve better generalization performance to a new task. For training large scale neural networks, we decompose the curvature matrix into smaller matrices in a novel scheme where we capture the dependencies of the model's parameters with a series of tensor products. We demonstrate the effects of our proposed method o","authors_text":"Eunbyung Park, Junier B. Oliva","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-09T02:34:53Z","title":"Meta-Curvature"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03356","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":"sha256:1e6b1047b64cbdb6aeab6b5ce169d4ff1d2caa0a6bcc07c903797509a100c754","target":"record","created_at":"2026-07-05T00:32:20Z","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":"70755639f9f8950a48116cbb9a269b416a231028c7e97159a4c8422b3b19a759","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-09T02:34:53Z","title_canon_sha256":"14a2e74da616a7a621a6ee301a255c8907d6e34f7c74ca13472c950c8079a969"},"schema_version":"1.0","source":{"id":"1902.03356","kind":"arxiv","version":3}},"canonical_sha256":"d0bf5c87ef6f0033157392c813159920db23603169a30ff43f2e6e4d01323f50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0bf5c87ef6f0033157392c813159920db23603169a30ff43f2e6e4d01323f50","first_computed_at":"2026-07-05T00:32:20.973060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:32:20.973060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Jf5y8c8dFAiVYXmL0AGlF2S8VgLujJMVQQNVjZnwzcGTQLMO0iIu0wKx95DpAQNfmSiddiWro3hYRIIjoj/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:32:20.973541Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.03356","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e6b1047b64cbdb6aeab6b5ce169d4ff1d2caa0a6bcc07c903797509a100c754","sha256:7c095d739d40cf1ac97e5053201780dd2d4e478cbf16fe2282c43c150eba315a"],"state_sha256":"d863bf344607a5ee8b4797e14521ee1a7e3ee5898435ef8b7bdfb030bc658ed7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W/wpofB50u7WYljC7rLSj9H3XWEB1TIzMI19yR6ilvTWZDq/jNfLuNVHjsXGDl0JhhLbq5C7Zt4Ss0v3zBhABQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T06:44:02.949303Z","bundle_sha256":"d5a5011205a518cc1073f1bbef6c292d379fc5e21dbe886858f41b40d10e4cba"}}