{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TD7Z7VQALGXJJ5F5UHBLYQGFWA","short_pith_number":"pith:TD7Z7VQA","canonical_record":{"source":{"id":"2203.10185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-18T22:43:16Z","cross_cats_sorted":[],"title_canon_sha256":"fe37574bf2f404777517c10ec6df1866f40571d35436b87f1b9f49d77495cb28","abstract_canon_sha256":"846cd3b6d711b3fc523682a7aaec456f1f44fd52579e465234256d094d3277bb"},"schema_version":"1.0"},"canonical_sha256":"98ff9fd60059ae94f4bda1c2bc40c5b017c901e403dfabc534c43f421a251988","source":{"kind":"arxiv","id":"2203.10185","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10185","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10185v1","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10185","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"TD7Z7VQALGXJ","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"pith_short_16","alias_value":"TD7Z7VQALGXJJ5F5","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"pith_short_8","alias_value":"TD7Z7VQA","created_at":"2026-07-05T04:06:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TD7Z7VQALGXJJ5F5UHBLYQGFWA","target":"record","payload":{"canonical_record":{"source":{"id":"2203.10185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-18T22:43:16Z","cross_cats_sorted":[],"title_canon_sha256":"fe37574bf2f404777517c10ec6df1866f40571d35436b87f1b9f49d77495cb28","abstract_canon_sha256":"846cd3b6d711b3fc523682a7aaec456f1f44fd52579e465234256d094d3277bb"},"schema_version":"1.0"},"canonical_sha256":"98ff9fd60059ae94f4bda1c2bc40c5b017c901e403dfabc534c43f421a251988","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:32.341629Z","signature_b64":"s6nILsEvBbUrJu4e8ajWUP8NuqTCvPejmgQo8CiPfF0lzfDE0TmnwTDQPASArHKBKhK8Kr92u+vNfh4OYVxkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98ff9fd60059ae94f4bda1c2bc40c5b017c901e403dfabc534c43f421a251988","last_reissued_at":"2026-07-05T04:06:32.341261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:32.341261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.10185","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":"2026-07-05T04:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XGtQQWmVQp4+NTP5iXDjddODGSSjWBjFZ3WVIUDKcDXpCaztvz1t6GngviFY+7xuwEo+8cg9WgzSIzGs0K6aCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:39:15.559860Z"},"content_sha256":"db0f8398ab1afbdb7c9f85ea512a3844904a7ad5d6d57c1f5aac20d52047ee61","schema_version":"1.0","event_id":"sha256:db0f8398ab1afbdb7c9f85ea512a3844904a7ad5d6d57c1f5aac20d52047ee61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TD7Z7VQALGXJJ5F5UHBLYQGFWA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Negative Inner-Loop Learning Rates Learn Universal Features","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tom Starshak","submitted_at":"2022-03-18T22:43:16Z","abstract_excerpt":"Model Agnostic Meta-Learning (MAML) consists of two optimization loops: the outer loop learns a meta-initialization of model parameters that is shared across tasks, and the inner loop task-specific adaptation step. A variant of MAML, Meta-SGD, uses the same two loop structure, but also learns the learning-rate for the adaptation step. Little attention has been paid to how the learned learning-rate of Meta-SGD affects feature reuse. In this paper, we study the effect that a learned learning-rate has on the per-task feature representations in Meta-SGD. The learned learning-rate of Meta-SGD often"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10185","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.10185/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":"2026-07-05T04:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SWDIwGuBQCn/NgBHCjihOj4lCt7NlKt9RFrJXQaVviZg96UNSfXYuMVtJtk2WWYrfNnwlJiu0tZBoNXk0kP6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:39:15.560796Z"},"content_sha256":"f0fb5f132889678ca2cf6978a8e814a3af9035d16b8b2e32591cd43b2959db65","schema_version":"1.0","event_id":"sha256:f0fb5f132889678ca2cf6978a8e814a3af9035d16b8b2e32591cd43b2959db65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TD7Z7VQALGXJJ5F5UHBLYQGFWA/bundle.json","state_url":"https://pith.science/pith/TD7Z7VQALGXJJ5F5UHBLYQGFWA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TD7Z7VQALGXJJ5F5UHBLYQGFWA/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":"2026-08-11T04:39:15Z","links":{"resolver":"https://pith.science/pith/TD7Z7VQALGXJJ5F5UHBLYQGFWA","bundle":"https://pith.science/pith/TD7Z7VQALGXJJ5F5UHBLYQGFWA/bundle.json","state":"https://pith.science/pith/TD7Z7VQALGXJJ5F5UHBLYQGFWA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TD7Z7VQALGXJJ5F5UHBLYQGFWA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TD7Z7VQALGXJJ5F5UHBLYQGFWA","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":"846cd3b6d711b3fc523682a7aaec456f1f44fd52579e465234256d094d3277bb","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-18T22:43:16Z","title_canon_sha256":"fe37574bf2f404777517c10ec6df1866f40571d35436b87f1b9f49d77495cb28"},"schema_version":"1.0","source":{"id":"2203.10185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10185","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10185v1","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10185","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"TD7Z7VQALGXJ","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"pith_short_16","alias_value":"TD7Z7VQALGXJJ5F5","created_at":"2026-07-05T04:06:32Z"},{"alias_kind":"pith_short_8","alias_value":"TD7Z7VQA","created_at":"2026-07-05T04:06:32Z"}],"graph_snapshots":[{"event_id":"sha256:f0fb5f132889678ca2cf6978a8e814a3af9035d16b8b2e32591cd43b2959db65","target":"graph","created_at":"2026-07-05T04:06:32Z","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/2203.10185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model Agnostic Meta-Learning (MAML) consists of two optimization loops: the outer loop learns a meta-initialization of model parameters that is shared across tasks, and the inner loop task-specific adaptation step. A variant of MAML, Meta-SGD, uses the same two loop structure, but also learns the learning-rate for the adaptation step. Little attention has been paid to how the learned learning-rate of Meta-SGD affects feature reuse. In this paper, we study the effect that a learned learning-rate has on the per-task feature representations in Meta-SGD. The learned learning-rate of Meta-SGD often","authors_text":"Tom Starshak","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-18T22:43:16Z","title":"Negative Inner-Loop Learning Rates Learn Universal Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10185","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:db0f8398ab1afbdb7c9f85ea512a3844904a7ad5d6d57c1f5aac20d52047ee61","target":"record","created_at":"2026-07-05T04:06:32Z","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":"846cd3b6d711b3fc523682a7aaec456f1f44fd52579e465234256d094d3277bb","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-18T22:43:16Z","title_canon_sha256":"fe37574bf2f404777517c10ec6df1866f40571d35436b87f1b9f49d77495cb28"},"schema_version":"1.0","source":{"id":"2203.10185","kind":"arxiv","version":1}},"canonical_sha256":"98ff9fd60059ae94f4bda1c2bc40c5b017c901e403dfabc534c43f421a251988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98ff9fd60059ae94f4bda1c2bc40c5b017c901e403dfabc534c43f421a251988","first_computed_at":"2026-07-05T04:06:32.341261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:32.341261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s6nILsEvBbUrJu4e8ajWUP8NuqTCvPejmgQo8CiPfF0lzfDE0TmnwTDQPASArHKBKhK8Kr92u+vNfh4OYVxkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:32.341629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db0f8398ab1afbdb7c9f85ea512a3844904a7ad5d6d57c1f5aac20d52047ee61","sha256:f0fb5f132889678ca2cf6978a8e814a3af9035d16b8b2e32591cd43b2959db65"],"state_sha256":"514bad0fd1df9a5bc80731150e06944a74eb69c4a974430724a5a0e9744b37df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"02cMzHtHcCV8VT3BrB+CqhN3KcBH9o+E7AOTLLga9KoW/Pl5Hlc0vg887SeGq9D7DgEiuOl54FMBjtXEz8SiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:39:16.339395Z","bundle_sha256":"e1928e1635bf4a3f58b8c3af7a42cc83ee0f367733a113225b52b93b11b6c541"}}