{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7H4N4F6WIX4ERDBZIFGUCHL2DE","short_pith_number":"pith:7H4N4F6W","canonical_record":{"source":{"id":"1904.03758","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T22:23:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c12b4ebf61f1b2191fb38e31e1e70b82270351b06d572e47271a58a5c3d08dc","abstract_canon_sha256":"f623654169f549aaaa95c830df7b370c2257f678936a328539ac50097e010f13"},"schema_version":"1.0"},"canonical_sha256":"f9f8de17d645f8488c39414d411d7a1914202f38b42b43959ea89e417831b3db","source":{"kind":"arxiv","id":"1904.03758","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03758","created_at":"2026-05-17T23:47:57Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03758v2","created_at":"2026-05-17T23:47:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03758","created_at":"2026-05-17T23:47:57Z"},{"alias_kind":"pith_short_12","alias_value":"7H4N4F6WIX4E","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7H4N4F6WIX4ERDBZ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7H4N4F6W","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7H4N4F6WIX4ERDBZIFGUCHL2DE","target":"record","payload":{"canonical_record":{"source":{"id":"1904.03758","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T22:23:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c12b4ebf61f1b2191fb38e31e1e70b82270351b06d572e47271a58a5c3d08dc","abstract_canon_sha256":"f623654169f549aaaa95c830df7b370c2257f678936a328539ac50097e010f13"},"schema_version":"1.0"},"canonical_sha256":"f9f8de17d645f8488c39414d411d7a1914202f38b42b43959ea89e417831b3db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:57.359804Z","signature_b64":"3Zvv2t4mqUjrWtM39YQCVZ4UtcDGgOwh6sIo7A0uPEMI9CUXa+aitBxnX/M69Z2dCkK/x/LnnWpIt8JD94dBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9f8de17d645f8488c39414d411d7a1914202f38b42b43959ea89e417831b3db","last_reissued_at":"2026-05-17T23:47:57.359336Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:57.359336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.03758","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eln4oWiy84sEFl2phbqlhYd3ywLUsl3RDEJ/Cj4LgVUrd2sKA7tTvjdnK7C4++PvelE/Bw2YYE4RXGZpz/l2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:04:57.729403Z"},"content_sha256":"822c7673e102ea8c200051f089e0f27cd4980b29d97d0b731a2b14552ab1963f","schema_version":"1.0","event_id":"sha256:822c7673e102ea8c200051f089e0f27cd4980b29d97d0b731a2b14552ab1963f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7H4N4F6WIX4ERDBZIFGUCHL2DE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Learning with Differentiable Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Avinash Ravichandran, Kwonjoon Lee, Stefano Soatto, Subhransu Maji","submitted_at":"2019-04-07T22:23:42Z","abstract_excerpt":"Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks. Our objective is to learn feature embeddings that generalize well under a linear classification rule for novel categories. To efficiently solve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03758","kind":"arxiv","version":2},"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":"2026-05-17T23:47:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRXgXouL63rFBafGbP7oUN84oF4OpMad0sv9P4yVEscWq/Q8hEJ2uQpaceu5HGvnFxL+DPleobJW0lyxrhb3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:04:57.729752Z"},"content_sha256":"76f0d02730d52d2ab21e4ed097b10d04f3d31a6601c7010996d89baf88f41ca7","schema_version":"1.0","event_id":"sha256:76f0d02730d52d2ab21e4ed097b10d04f3d31a6601c7010996d89baf88f41ca7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7H4N4F6WIX4ERDBZIFGUCHL2DE/bundle.json","state_url":"https://pith.science/pith/7H4N4F6WIX4ERDBZIFGUCHL2DE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7H4N4F6WIX4ERDBZIFGUCHL2DE/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":"2026-06-20T02:04:57Z","links":{"resolver":"https://pith.science/pith/7H4N4F6WIX4ERDBZIFGUCHL2DE","bundle":"https://pith.science/pith/7H4N4F6WIX4ERDBZIFGUCHL2DE/bundle.json","state":"https://pith.science/pith/7H4N4F6WIX4ERDBZIFGUCHL2DE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7H4N4F6WIX4ERDBZIFGUCHL2DE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7H4N4F6WIX4ERDBZIFGUCHL2DE","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":"f623654169f549aaaa95c830df7b370c2257f678936a328539ac50097e010f13","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T22:23:42Z","title_canon_sha256":"9c12b4ebf61f1b2191fb38e31e1e70b82270351b06d572e47271a58a5c3d08dc"},"schema_version":"1.0","source":{"id":"1904.03758","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03758","created_at":"2026-05-17T23:47:57Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03758v2","created_at":"2026-05-17T23:47:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03758","created_at":"2026-05-17T23:47:57Z"},{"alias_kind":"pith_short_12","alias_value":"7H4N4F6WIX4E","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7H4N4F6WIX4ERDBZ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7H4N4F6W","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:76f0d02730d52d2ab21e4ed097b10d04f3d31a6601c7010996d89baf88f41ca7","target":"graph","created_at":"2026-05-17T23:47:57Z","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":"Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks. Our objective is to learn feature embeddings that generalize well under a linear classification rule for novel categories. To efficiently solve","authors_text":"Avinash Ravichandran, Kwonjoon Lee, Stefano Soatto, Subhransu Maji","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T22:23:42Z","title":"Meta-Learning with Differentiable Convex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03758","kind":"arxiv","version":2},"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":"sha256:822c7673e102ea8c200051f089e0f27cd4980b29d97d0b731a2b14552ab1963f","target":"record","created_at":"2026-05-17T23:47:57Z","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":"f623654169f549aaaa95c830df7b370c2257f678936a328539ac50097e010f13","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T22:23:42Z","title_canon_sha256":"9c12b4ebf61f1b2191fb38e31e1e70b82270351b06d572e47271a58a5c3d08dc"},"schema_version":"1.0","source":{"id":"1904.03758","kind":"arxiv","version":2}},"canonical_sha256":"f9f8de17d645f8488c39414d411d7a1914202f38b42b43959ea89e417831b3db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9f8de17d645f8488c39414d411d7a1914202f38b42b43959ea89e417831b3db","first_computed_at":"2026-05-17T23:47:57.359336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:57.359336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Zvv2t4mqUjrWtM39YQCVZ4UtcDGgOwh6sIo7A0uPEMI9CUXa+aitBxnX/M69Z2dCkK/x/LnnWpIt8JD94dBAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:57.359804Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03758","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:822c7673e102ea8c200051f089e0f27cd4980b29d97d0b731a2b14552ab1963f","sha256:76f0d02730d52d2ab21e4ed097b10d04f3d31a6601c7010996d89baf88f41ca7"],"state_sha256":"a585bc2ac274d8031aeeb49288cce7456adac1b17140f44382cb1dc55a274dba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gbT/YXMdWDaHxmMojdWPDVlTvZUGL1auJ0yKqBYOLPxEkrFMvg6qm9rKkeihjjkVvrcOYNJqweANOITQuOIDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T02:04:57.731727Z","bundle_sha256":"6af52a995a788496f1ded71d2cee01e079f4650e82481c31b0a3243428a431e4"}}