{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2XYEB6NVDBJMFMPH2QB2RSCZY5","short_pith_number":"pith:2XYEB6NV","canonical_record":{"source":{"id":"1907.02549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:22:23Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"4dcdbb35801988a208a40976a3a0f27540afb3f9e9f51c83cdd73ec09ce89e66","abstract_canon_sha256":"1affec663931a2756a72b0788da8bf825a1ce9c75cd978961e885b7bb5263b36"},"schema_version":"1.0"},"canonical_sha256":"d5f040f9b51852c2b1e7d403a8c859c77996074a817242c994f6bb2b47b9b54d","source":{"kind":"arxiv","id":"1907.02549","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02549","created_at":"2026-05-17T23:41:24Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02549v1","created_at":"2026-05-17T23:41:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02549","created_at":"2026-05-17T23:41:24Z"},{"alias_kind":"pith_short_12","alias_value":"2XYEB6NVDBJM","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2XYEB6NVDBJMFMPH","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2XYEB6NV","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2XYEB6NVDBJMFMPH2QB2RSCZY5","target":"record","payload":{"canonical_record":{"source":{"id":"1907.02549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:22:23Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"4dcdbb35801988a208a40976a3a0f27540afb3f9e9f51c83cdd73ec09ce89e66","abstract_canon_sha256":"1affec663931a2756a72b0788da8bf825a1ce9c75cd978961e885b7bb5263b36"},"schema_version":"1.0"},"canonical_sha256":"d5f040f9b51852c2b1e7d403a8c859c77996074a817242c994f6bb2b47b9b54d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:24.055141Z","signature_b64":"Z68GQyWOVnXLMB2m+5Xx6aaxZtebs0u9wTF7+5q8fZZZ1nx9Hj91JDmWvfUHUekd/X7OpdEcbRnRMf3njChyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5f040f9b51852c2b1e7d403a8c859c77996074a817242c994f6bb2b47b9b54d","last_reissued_at":"2026-05-17T23:41:24.054479Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:24.054479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.02549","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":"2026-05-17T23:41:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hqJHVID0QOaOh0QJNFXVePoZUWQW8xmn0x4acpg6kh42lAq69cb67rPfTvu8V1en9NY2PLxKMfuPeatmFiKwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:29:39.382331Z"},"content_sha256":"d2fbce0e54f87b9284f83661d99e44cf017bb66e573333980dfe91299c236bb5","schema_version":"1.0","event_id":"sha256:d2fbce0e54f87b9284f83661d99e44cf017bb66e573333980dfe91299c236bb5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2XYEB6NVDBJMFMPH2QB2RSCZY5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring the Data Efficiency of Deep Learning Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto N. Escalante-B., Hlynur Dav\\'i{\\dh} Hlynsson, Laurenz Wiskott","submitted_at":"2019-07-03T15:22:23Z","abstract_excerpt":"In this paper, we propose a new experimental protocol and use it to benchmark the data efficiency --- performance as a function of training set size --- of two deep learning algorithms, convolutional neural networks (CNNs) and hierarchical information-preserving graph-based slow feature analysis (HiGSFA), for tasks in classification and transfer learning scenarios. The algorithms are trained on different-sized subsets of the MNIST and Omniglot data sets. HiGSFA outperforms standard CNN networks when the models are trained on 50 and 200 samples per class for MNIST classification. In other cases"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02549","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":"2026-05-17T23:41:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fJRX9+FdlDU7tDUNshD42QZgZ3G+C40mXT0zNYAZ7reqzXrv2xq1vGFj1svVDQrmkf42oXfTK9glvCOBKrUvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:29:39.382688Z"},"content_sha256":"9cbe7abe94a9678f0eb03377b87cb3e17252f8739f1c5183f5b477eb2b7a54c0","schema_version":"1.0","event_id":"sha256:9cbe7abe94a9678f0eb03377b87cb3e17252f8739f1c5183f5b477eb2b7a54c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2XYEB6NVDBJMFMPH2QB2RSCZY5/bundle.json","state_url":"https://pith.science/pith/2XYEB6NVDBJMFMPH2QB2RSCZY5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2XYEB6NVDBJMFMPH2QB2RSCZY5/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":"2026-06-11T10:29:39Z","links":{"resolver":"https://pith.science/pith/2XYEB6NVDBJMFMPH2QB2RSCZY5","bundle":"https://pith.science/pith/2XYEB6NVDBJMFMPH2QB2RSCZY5/bundle.json","state":"https://pith.science/pith/2XYEB6NVDBJMFMPH2QB2RSCZY5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2XYEB6NVDBJMFMPH2QB2RSCZY5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2XYEB6NVDBJMFMPH2QB2RSCZY5","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":"1affec663931a2756a72b0788da8bf825a1ce9c75cd978961e885b7bb5263b36","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:22:23Z","title_canon_sha256":"4dcdbb35801988a208a40976a3a0f27540afb3f9e9f51c83cdd73ec09ce89e66"},"schema_version":"1.0","source":{"id":"1907.02549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02549","created_at":"2026-05-17T23:41:24Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02549v1","created_at":"2026-05-17T23:41:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02549","created_at":"2026-05-17T23:41:24Z"},{"alias_kind":"pith_short_12","alias_value":"2XYEB6NVDBJM","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2XYEB6NVDBJMFMPH","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2XYEB6NV","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:9cbe7abe94a9678f0eb03377b87cb3e17252f8739f1c5183f5b477eb2b7a54c0","target":"graph","created_at":"2026-05-17T23:41:24Z","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"},"paper":{"abstract_excerpt":"In this paper, we propose a new experimental protocol and use it to benchmark the data efficiency --- performance as a function of training set size --- of two deep learning algorithms, convolutional neural networks (CNNs) and hierarchical information-preserving graph-based slow feature analysis (HiGSFA), for tasks in classification and transfer learning scenarios. The algorithms are trained on different-sized subsets of the MNIST and Omniglot data sets. HiGSFA outperforms standard CNN networks when the models are trained on 50 and 200 samples per class for MNIST classification. In other cases","authors_text":"Alberto N. Escalante-B., Hlynur Dav\\'i{\\dh} Hlynsson, Laurenz Wiskott","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:22:23Z","title":"Measuring the Data Efficiency of Deep Learning Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02549","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:d2fbce0e54f87b9284f83661d99e44cf017bb66e573333980dfe91299c236bb5","target":"record","created_at":"2026-05-17T23:41:24Z","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":"1affec663931a2756a72b0788da8bf825a1ce9c75cd978961e885b7bb5263b36","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:22:23Z","title_canon_sha256":"4dcdbb35801988a208a40976a3a0f27540afb3f9e9f51c83cdd73ec09ce89e66"},"schema_version":"1.0","source":{"id":"1907.02549","kind":"arxiv","version":1}},"canonical_sha256":"d5f040f9b51852c2b1e7d403a8c859c77996074a817242c994f6bb2b47b9b54d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5f040f9b51852c2b1e7d403a8c859c77996074a817242c994f6bb2b47b9b54d","first_computed_at":"2026-05-17T23:41:24.054479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:24.054479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z68GQyWOVnXLMB2m+5Xx6aaxZtebs0u9wTF7+5q8fZZZ1nx9Hj91JDmWvfUHUekd/X7OpdEcbRnRMf3njChyBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:24.055141Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.02549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2fbce0e54f87b9284f83661d99e44cf017bb66e573333980dfe91299c236bb5","sha256:9cbe7abe94a9678f0eb03377b87cb3e17252f8739f1c5183f5b477eb2b7a54c0"],"state_sha256":"e427eeb65723e65e330d1e9f753ca6d5654662a5fbf1cac707777e3fee178312"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qAj2zGgel9zJrABmC5TSf0LWPpuBXuxq+OOqDcbVqK7xu/0ESor1W2W4LpBWYint4rsdCwN3BuEJWNVZqQTVDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T10:29:39.384737Z","bundle_sha256":"bb6716f6c363350c4a91721db212a3f980bf382cefd00d4047afad520d312e74"}}