{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3CEP6GGBNU3NPGVXH6ZG2TWAP3","short_pith_number":"pith:3CEP6GGB","canonical_record":{"source":{"id":"1808.08833","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T13:08:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b89bf29cc3f4067690146c53f9c543c0a0d52ab6a820be50abf7f851bcc220e2","abstract_canon_sha256":"89862154321416a5e38a7e6f86b6aeb514a454d0bbda0f21fc2ccf1c1b2069d5"},"schema_version":"1.0"},"canonical_sha256":"d888ff18c16d36d79ab73fb26d4ec07edcf670a2efd5f500095f6687457d8a80","source":{"kind":"arxiv","id":"1808.08833","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08833","created_at":"2026-05-17T23:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08833v3","created_at":"2026-05-17T23:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08833","created_at":"2026-05-17T23:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"3CEP6GGBNU3N","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3CEP6GGBNU3NPGVX","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3CEP6GGB","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3CEP6GGBNU3NPGVXH6ZG2TWAP3","target":"record","payload":{"canonical_record":{"source":{"id":"1808.08833","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T13:08:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b89bf29cc3f4067690146c53f9c543c0a0d52ab6a820be50abf7f851bcc220e2","abstract_canon_sha256":"89862154321416a5e38a7e6f86b6aeb514a454d0bbda0f21fc2ccf1c1b2069d5"},"schema_version":"1.0"},"canonical_sha256":"d888ff18c16d36d79ab73fb26d4ec07edcf670a2efd5f500095f6687457d8a80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:18.086143Z","signature_b64":"3ydVNc1vU68zKew7g4WB8KemgmYWhPV3Dxw3CaegGZxpSW2BQdsW9nF+uQUplupbAubTugDcHqxRGfQfAPXUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d888ff18c16d36d79ab73fb26d4ec07edcf670a2efd5f500095f6687457d8a80","last_reissued_at":"2026-05-17T23:40:18.085650Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:18.085650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.08833","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":"2026-05-17T23:40:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KrxweWKEzg0fTnc7seOnacg1857pNccoQTjJlTN+Sto3njZFizZNuKmPwHQxmGtjscDHmwPOx2zFli572GAnCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T09:25:57.485155Z"},"content_sha256":"133f60c9a2f0894ddbf935c2e73a3583db76a33fb4c7cc2c0c7c7cc481cce178","schema_version":"1.0","event_id":"sha256:133f60c9a2f0894ddbf935c2e73a3583db76a33fb4c7cc2c0c7c7cc481cce178"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3CEP6GGBNU3NPGVXH6ZG2TWAP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hlynur Dav\\'i{\\dh} Hlynsson, Laurenz Wiskott, Merlin Sch\\\"uler","submitted_at":"2018-08-27T13:08:43Z","abstract_excerpt":"We propose Power Slow Feature Analysis, a gradient-based method to extract temporally slow features from a high-dimensional input stream that varies on a faster time-scale, as a variant of Slow Feature Analysis (SFA) that allows end-to-end training of arbitrary differentiable architectures and thereby significantly extends the class of models that can effectively be used for slow feature extraction. We provide experimental evidence that PowerSFA is able to extract meaningful and informative low-dimensional features in the case of (a) synthetic low-dimensional data, (b) ego-visual data, and als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08833","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":""},"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":"2026-05-17T23:40:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rECyhBKHtUVT6B31Ur+4xqT2cQh76OxRPzaygrG/YnQ6VtqrrTQhBF2eusmGduMLfFlP3clGtbK07ZVo6FdYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T09:25:57.485522Z"},"content_sha256":"7e544de43574fcab836e396ec1af7700e7225a9b2b5a39a311f0ef70adcfd58c","schema_version":"1.0","event_id":"sha256:7e544de43574fcab836e396ec1af7700e7225a9b2b5a39a311f0ef70adcfd58c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CEP6GGBNU3NPGVXH6ZG2TWAP3/bundle.json","state_url":"https://pith.science/pith/3CEP6GGBNU3NPGVXH6ZG2TWAP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CEP6GGBNU3NPGVXH6ZG2TWAP3/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":"2026-06-11T09:25:57Z","links":{"resolver":"https://pith.science/pith/3CEP6GGBNU3NPGVXH6ZG2TWAP3","bundle":"https://pith.science/pith/3CEP6GGBNU3NPGVXH6ZG2TWAP3/bundle.json","state":"https://pith.science/pith/3CEP6GGBNU3NPGVXH6ZG2TWAP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CEP6GGBNU3NPGVXH6ZG2TWAP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3CEP6GGBNU3NPGVXH6ZG2TWAP3","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":"89862154321416a5e38a7e6f86b6aeb514a454d0bbda0f21fc2ccf1c1b2069d5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T13:08:43Z","title_canon_sha256":"b89bf29cc3f4067690146c53f9c543c0a0d52ab6a820be50abf7f851bcc220e2"},"schema_version":"1.0","source":{"id":"1808.08833","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08833","created_at":"2026-05-17T23:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08833v3","created_at":"2026-05-17T23:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08833","created_at":"2026-05-17T23:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"3CEP6GGBNU3N","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3CEP6GGBNU3NPGVX","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3CEP6GGB","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:7e544de43574fcab836e396ec1af7700e7225a9b2b5a39a311f0ef70adcfd58c","target":"graph","created_at":"2026-05-17T23:40:18Z","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":"We propose Power Slow Feature Analysis, a gradient-based method to extract temporally slow features from a high-dimensional input stream that varies on a faster time-scale, as a variant of Slow Feature Analysis (SFA) that allows end-to-end training of arbitrary differentiable architectures and thereby significantly extends the class of models that can effectively be used for slow feature extraction. We provide experimental evidence that PowerSFA is able to extract meaningful and informative low-dimensional features in the case of (a) synthetic low-dimensional data, (b) ego-visual data, and als","authors_text":"Hlynur Dav\\'i{\\dh} Hlynsson, Laurenz Wiskott, Merlin Sch\\\"uler","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T13:08:43Z","title":"Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08833","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":"sha256:133f60c9a2f0894ddbf935c2e73a3583db76a33fb4c7cc2c0c7c7cc481cce178","target":"record","created_at":"2026-05-17T23:40:18Z","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":"89862154321416a5e38a7e6f86b6aeb514a454d0bbda0f21fc2ccf1c1b2069d5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T13:08:43Z","title_canon_sha256":"b89bf29cc3f4067690146c53f9c543c0a0d52ab6a820be50abf7f851bcc220e2"},"schema_version":"1.0","source":{"id":"1808.08833","kind":"arxiv","version":3}},"canonical_sha256":"d888ff18c16d36d79ab73fb26d4ec07edcf670a2efd5f500095f6687457d8a80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d888ff18c16d36d79ab73fb26d4ec07edcf670a2efd5f500095f6687457d8a80","first_computed_at":"2026-05-17T23:40:18.085650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:18.085650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ydVNc1vU68zKew7g4WB8KemgmYWhPV3Dxw3CaegGZxpSW2BQdsW9nF+uQUplupbAubTugDcHqxRGfQfAPXUAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:18.086143Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.08833","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:133f60c9a2f0894ddbf935c2e73a3583db76a33fb4c7cc2c0c7c7cc481cce178","sha256:7e544de43574fcab836e396ec1af7700e7225a9b2b5a39a311f0ef70adcfd58c"],"state_sha256":"647bbf19220a5bb71f16b02c8598a3da4afb1d4c3b0d05f6d2afebab944b9f1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kSs+3nVuqOElFzr8H4VDAwsCNqTI1JJw2m0usqTLjyNF36wLe6Y8vH5aAs5JdlCVHpTR6xCuHG4NkrDn+ytpCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T09:25:57.487497Z","bundle_sha256":"46b0d74afbc45c0bec9fdd2536a8e8a10d45f1f5dea12e6769d21d1d46e9a815"}}