{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3HXK7JMVMBUN65JZT5WM4YEV2Z","short_pith_number":"pith:3HXK7JMV","canonical_record":{"source":{"id":"2002.06753","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T03:18:45Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"988e18177311ca0920194c0e6b83c8041e0eabbbe2da0f9e816f92929e04aec2","abstract_canon_sha256":"65992aeca33e4eadaac7fae77c8dce9b6b585a3ccecaa84ac466808014f83db7"},"schema_version":"1.0"},"canonical_sha256":"d9eeafa5956068df75399f6cce6095d64fcc75315283d0ed35f84c89b1af1685","source":{"kind":"arxiv","id":"2002.06753","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06753","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06753v3","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06753","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"3HXK7JMVMBUN","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"3HXK7JMVMBUN65JZ","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"3HXK7JMV","created_at":"2026-07-05T01:15:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3HXK7JMVMBUN65JZT5WM4YEV2Z","target":"record","payload":{"canonical_record":{"source":{"id":"2002.06753","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T03:18:45Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"988e18177311ca0920194c0e6b83c8041e0eabbbe2da0f9e816f92929e04aec2","abstract_canon_sha256":"65992aeca33e4eadaac7fae77c8dce9b6b585a3ccecaa84ac466808014f83db7"},"schema_version":"1.0"},"canonical_sha256":"d9eeafa5956068df75399f6cce6095d64fcc75315283d0ed35f84c89b1af1685","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:24.556156Z","signature_b64":"4qYohcs7NlpYp3HY0fqqgDc5kxCStRmHc83Ag8T9kYsB0pTqo9pUhauTMQikqwCY0tv2mwMGL9loEmI2O5SrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9eeafa5956068df75399f6cce6095d64fcc75315283d0ed35f84c89b1af1685","last_reissued_at":"2026-07-05T01:15:24.555668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:24.555668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.06753","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":"2026-07-05T01:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B/5+NZqIs9kLBqW9/kILNtnmbLh1k406p3iRieUv4uhP0NBHMaulX5ppDjs2b0LWfBTFt9+i0QWrkG9Vq5WpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:01:29.448712Z"},"content_sha256":"e3a3347fa2059914f611eadfd24a2971ddc7193130cdd0f539cf3bd288e431d4","schema_version":"1.0","event_id":"sha256:e3a3347fa2059914f611eadfd24a2971ddc7193130cdd0f539cf3bd288e431d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3HXK7JMVMBUN65JZT5WM4YEV2Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Liam Fowl, Micah Goldblum, Renkun Ni, Steven Reich, Tom Goldstein, Valeriia Cherepanova","submitted_at":"2020-02-17T03:18:45Z","abstract_excerpt":"Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the underlying mechanics of meta-learning and the difference between models trained using meta-learning and models which are trained classically. In doing so, we introduce and verify several hypotheses for why meta-learned models perform better. Furthermore, we develop a regularizer which boosts the perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06753","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/2002.06753/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":"2026-07-05T01:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RoM3JKj9mb48Ekig1R7A31KFR2g9bnDF7sQ1bJuOJYwLQST6Ch34rPpgYHAFlCsCurVthc1worTLKHgWlJuuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:01:29.449092Z"},"content_sha256":"c3c99536b2d4998b3e910feb5fa506bb7b3ff1b14f4071ef9958a1495b1a8700","schema_version":"1.0","event_id":"sha256:c3c99536b2d4998b3e910feb5fa506bb7b3ff1b14f4071ef9958a1495b1a8700"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3HXK7JMVMBUN65JZT5WM4YEV2Z/bundle.json","state_url":"https://pith.science/pith/3HXK7JMVMBUN65JZT5WM4YEV2Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3HXK7JMVMBUN65JZT5WM4YEV2Z/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":"2026-07-05T15:01:29Z","links":{"resolver":"https://pith.science/pith/3HXK7JMVMBUN65JZT5WM4YEV2Z","bundle":"https://pith.science/pith/3HXK7JMVMBUN65JZT5WM4YEV2Z/bundle.json","state":"https://pith.science/pith/3HXK7JMVMBUN65JZT5WM4YEV2Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3HXK7JMVMBUN65JZT5WM4YEV2Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3HXK7JMVMBUN65JZT5WM4YEV2Z","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":"65992aeca33e4eadaac7fae77c8dce9b6b585a3ccecaa84ac466808014f83db7","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T03:18:45Z","title_canon_sha256":"988e18177311ca0920194c0e6b83c8041e0eabbbe2da0f9e816f92929e04aec2"},"schema_version":"1.0","source":{"id":"2002.06753","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06753","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06753v3","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06753","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"3HXK7JMVMBUN","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"3HXK7JMVMBUN65JZ","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"3HXK7JMV","created_at":"2026-07-05T01:15:24Z"}],"graph_snapshots":[{"event_id":"sha256:c3c99536b2d4998b3e910feb5fa506bb7b3ff1b14f4071ef9958a1495b1a8700","target":"graph","created_at":"2026-07-05T01:15:24Z","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/2002.06753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the underlying mechanics of meta-learning and the difference between models trained using meta-learning and models which are trained classically. In doing so, we introduce and verify several hypotheses for why meta-learned models perform better. Furthermore, we develop a regularizer which boosts the perfor","authors_text":"Liam Fowl, Micah Goldblum, Renkun Ni, Steven Reich, Tom Goldstein, Valeriia Cherepanova","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T03:18:45Z","title":"Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06753","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:e3a3347fa2059914f611eadfd24a2971ddc7193130cdd0f539cf3bd288e431d4","target":"record","created_at":"2026-07-05T01:15:24Z","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":"65992aeca33e4eadaac7fae77c8dce9b6b585a3ccecaa84ac466808014f83db7","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T03:18:45Z","title_canon_sha256":"988e18177311ca0920194c0e6b83c8041e0eabbbe2da0f9e816f92929e04aec2"},"schema_version":"1.0","source":{"id":"2002.06753","kind":"arxiv","version":3}},"canonical_sha256":"d9eeafa5956068df75399f6cce6095d64fcc75315283d0ed35f84c89b1af1685","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9eeafa5956068df75399f6cce6095d64fcc75315283d0ed35f84c89b1af1685","first_computed_at":"2026-07-05T01:15:24.555668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:15:24.555668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4qYohcs7NlpYp3HY0fqqgDc5kxCStRmHc83Ag8T9kYsB0pTqo9pUhauTMQikqwCY0tv2mwMGL9loEmI2O5SrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:15:24.556156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06753","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3a3347fa2059914f611eadfd24a2971ddc7193130cdd0f539cf3bd288e431d4","sha256:c3c99536b2d4998b3e910feb5fa506bb7b3ff1b14f4071ef9958a1495b1a8700"],"state_sha256":"4bc34e9603252a5d193dfa054bac6db017d850c81c27d8c77225ce7105905c8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+RXdeprD/bdQ/8asMjjAHdxdWvUuT3bpHZ5Z9kAeS7v1q2+BUDBr8NO3qRrpSKGYmyEeE2w06e4K4fRkVoS6Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:01:29.451700Z","bundle_sha256":"3d24b39ec536669c4ed4fe5d7101a3f5092a6b82cc5974bb8852e07822b0760f"}}