{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:Q4YHNX4LG6Q3FLXTA35BABFKGL","short_pith_number":"pith:Q4YHNX4L","canonical_record":{"source":{"id":"1906.03367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T01:08:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2c9946b5403cc398e19508b19c0faa699c0b1f233d97cf4cba99e96109aeb72","abstract_canon_sha256":"73041aa0ff18c9545345274dd6c8ac5c6d9c479465dbdb6a450f3140a1eb5c72"},"schema_version":"1.0"},"canonical_sha256":"873076df8b37a1b2aef306fa1004aa32c36b9e6513b7a561a1244f40246ecb21","source":{"kind":"arxiv","id":"1906.03367","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03367","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03367v1","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03367","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"Q4YHNX4LG6Q3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"Q4YHNX4LG6Q3FLXT","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"Q4YHNX4L","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:Q4YHNX4LG6Q3FLXTA35BABFKGL","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T01:08:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2c9946b5403cc398e19508b19c0faa699c0b1f233d97cf4cba99e96109aeb72","abstract_canon_sha256":"73041aa0ff18c9545345274dd6c8ac5c6d9c479465dbdb6a450f3140a1eb5c72"},"schema_version":"1.0"},"canonical_sha256":"873076df8b37a1b2aef306fa1004aa32c36b9e6513b7a561a1244f40246ecb21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:48.696592Z","signature_b64":"S13x9yoeJ9P+oXBtd3MEtaDM5BUdN97bS/58Z7WqIRJ4MrR8XxG5EkFeZpYj0u0/uY99iqafJmHso5NZ+IHdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"873076df8b37a1b2aef306fa1004aa32c36b9e6513b7a561a1244f40246ecb21","last_reissued_at":"2026-05-17T23:43:48.695965Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:48.695965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03367","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":"2026-05-17T23:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eVghGmK2c6MIvw3/KvMiQ86rxE99W/bDmLzZDhL8UaMqyiYA68NlXo+tB3WSuYxFGvROY2lZ0ND2s2io7jOMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:04:19.468104Z"},"content_sha256":"8f9ca9d582b26f2dd8e9089da98b214983a72ed0d562e5d7ba0d64b8e720f457","schema_version":"1.0","event_id":"sha256:8f9ca9d582b26f2dd8e9089da98b214983a72ed0d562e5d7ba0d64b8e720f457"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:Q4YHNX4LG6Q3FLXTA35BABFKGL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using learned optimizers to make models robust to input noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ekin D. Cubuk, Jascha Sohl-Dickstein, Jonathon Shlens, Luke Metz, Niru Maheswaranathan","submitted_at":"2019-06-08T01:08:36Z","abstract_excerpt":"State-of-the art vision models can achieve superhuman performance on image classification tasks when testing and training data come from the same distribution. However, when models are tested on corrupted images (e.g. due to scale changes, translations, or shifts in brightness or contrast), performance degrades significantly. Here, we explore the possibility of meta-training a learned optimizer that can train image classification models such that they are robust to common image corruptions. Specifically, we are interested training models that are more robust to noise distributions not present "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03367","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":"2026-05-17T23:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M+OCNytJgYoG7q6pJ33dqEpgau4vw5pmpNm2J5hxRjQd8EpoHQQUCffD1Z0nXdiz8bqN4zMnnegfBEa9SMi4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:04:19.468813Z"},"content_sha256":"b582b28f8e76f2a814c46cca426b2e6c1348fc6fb589900ecc1bc26d7ae77d95","schema_version":"1.0","event_id":"sha256:b582b28f8e76f2a814c46cca426b2e6c1348fc6fb589900ecc1bc26d7ae77d95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4YHNX4LG6Q3FLXTA35BABFKGL/bundle.json","state_url":"https://pith.science/pith/Q4YHNX4LG6Q3FLXTA35BABFKGL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4YHNX4LG6Q3FLXTA35BABFKGL/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":"2026-05-28T23:04:19Z","links":{"resolver":"https://pith.science/pith/Q4YHNX4LG6Q3FLXTA35BABFKGL","bundle":"https://pith.science/pith/Q4YHNX4LG6Q3FLXTA35BABFKGL/bundle.json","state":"https://pith.science/pith/Q4YHNX4LG6Q3FLXTA35BABFKGL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4YHNX4LG6Q3FLXTA35BABFKGL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Q4YHNX4LG6Q3FLXTA35BABFKGL","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":"73041aa0ff18c9545345274dd6c8ac5c6d9c479465dbdb6a450f3140a1eb5c72","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T01:08:36Z","title_canon_sha256":"e2c9946b5403cc398e19508b19c0faa699c0b1f233d97cf4cba99e96109aeb72"},"schema_version":"1.0","source":{"id":"1906.03367","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03367","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03367v1","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03367","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"Q4YHNX4LG6Q3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"Q4YHNX4LG6Q3FLXT","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"Q4YHNX4L","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:b582b28f8e76f2a814c46cca426b2e6c1348fc6fb589900ecc1bc26d7ae77d95","target":"graph","created_at":"2026-05-17T23:43:48Z","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":"State-of-the art vision models can achieve superhuman performance on image classification tasks when testing and training data come from the same distribution. However, when models are tested on corrupted images (e.g. due to scale changes, translations, or shifts in brightness or contrast), performance degrades significantly. Here, we explore the possibility of meta-training a learned optimizer that can train image classification models such that they are robust to common image corruptions. Specifically, we are interested training models that are more robust to noise distributions not present ","authors_text":"Ekin D. Cubuk, Jascha Sohl-Dickstein, Jonathon Shlens, Luke Metz, Niru Maheswaranathan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T01:08:36Z","title":"Using learned optimizers to make models robust to input noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03367","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":"sha256:8f9ca9d582b26f2dd8e9089da98b214983a72ed0d562e5d7ba0d64b8e720f457","target":"record","created_at":"2026-05-17T23:43:48Z","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":"73041aa0ff18c9545345274dd6c8ac5c6d9c479465dbdb6a450f3140a1eb5c72","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T01:08:36Z","title_canon_sha256":"e2c9946b5403cc398e19508b19c0faa699c0b1f233d97cf4cba99e96109aeb72"},"schema_version":"1.0","source":{"id":"1906.03367","kind":"arxiv","version":1}},"canonical_sha256":"873076df8b37a1b2aef306fa1004aa32c36b9e6513b7a561a1244f40246ecb21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"873076df8b37a1b2aef306fa1004aa32c36b9e6513b7a561a1244f40246ecb21","first_computed_at":"2026-05-17T23:43:48.695965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:48.695965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S13x9yoeJ9P+oXBtd3MEtaDM5BUdN97bS/58Z7WqIRJ4MrR8XxG5EkFeZpYj0u0/uY99iqafJmHso5NZ+IHdDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:48.696592Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03367","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f9ca9d582b26f2dd8e9089da98b214983a72ed0d562e5d7ba0d64b8e720f457","sha256:b582b28f8e76f2a814c46cca426b2e6c1348fc6fb589900ecc1bc26d7ae77d95"],"state_sha256":"da3e9a2d6d2685c4d1e631727a5242ac56a3ebc90e940ace760809a3fbc1df98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"994vMl+1lO58IAxthXItfaWN0Gr96Grq+GfaiIo7V6MWIkoLMoYZxHj8raga5RwSEVNTE68gHWe5qXeDgmV+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:04:19.472768Z","bundle_sha256":"30845de2322e471a98927ffe51953659ae603e28c9e0a2bd5654c16f960d16d5"}}