{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:H4Z3ZCDUT4BQJVWSQ2KFEADR7M","short_pith_number":"pith:H4Z3ZCDU","canonical_record":{"source":{"id":"1810.04066","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T15:15:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"82af8801b8bc169d2fc7a5229112decc9e79de3fb29e247eb3cfa7efc4fadf3e","abstract_canon_sha256":"990985eeffd8b668365b3825b70ffdba1ee304b202223ec89ea2a5f032206b9e"},"schema_version":"1.0"},"canonical_sha256":"3f33bc88749f0304d6d28694520071fb313f46095fef58a47364ff02416ac55f","source":{"kind":"arxiv","id":"1810.04066","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04066","created_at":"2026-05-18T00:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04066v2","created_at":"2026-05-18T00:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04066","created_at":"2026-05-18T00:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"H4Z3ZCDUT4BQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H4Z3ZCDUT4BQJVWS","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H4Z3ZCDU","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:H4Z3ZCDUT4BQJVWSQ2KFEADR7M","target":"record","payload":{"canonical_record":{"source":{"id":"1810.04066","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T15:15:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"82af8801b8bc169d2fc7a5229112decc9e79de3fb29e247eb3cfa7efc4fadf3e","abstract_canon_sha256":"990985eeffd8b668365b3825b70ffdba1ee304b202223ec89ea2a5f032206b9e"},"schema_version":"1.0"},"canonical_sha256":"3f33bc88749f0304d6d28694520071fb313f46095fef58a47364ff02416ac55f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:23.933657Z","signature_b64":"+eMLi7JkrYQ9Jgr/EEZOgvew6KVvxsb1EDZEO1Gs72Wi1nNCK+aK8qCdNJUYtmw3aeQ4sKM2O2GhHXVY5LpsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f33bc88749f0304d6d28694520071fb313f46095fef58a47364ff02416ac55f","last_reissued_at":"2026-05-18T00:03:23.933010Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:23.933010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.04066","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":"2026-05-18T00:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a/5/PfKCmPNnhu19/ZTrqp2DEQt6RRygcnBlJZc+9dgyUW9cSIKWV8B9syDH8b0BoxVGHW6XPGhHG4Y7qjepBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:09:05.590571Z"},"content_sha256":"49d4252913c21c1e82f750e7b422e1fa4faf3af83d4ef469a069f4684b03584d","schema_version":"1.0","event_id":"sha256:49d4252913c21c1e82f750e7b422e1fa4faf3af83d4ef469a069f4684b03584d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:H4Z3ZCDUT4BQJVWSQ2KFEADR7M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep learning with differential Gaussian process flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Harri L\\\"ahdesm\\\"aki, Markus Heinonen, Pashupati Hegde, Samuel Kaski","submitted_at":"2018-10-09T15:15:23Z","abstract_excerpt":"We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04066","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":"2026-05-18T00:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o37+bH69dMI5d1ZPB15y8aRJUozTfxC1DKdR1xEOYB60OEMwtFZ3bzXV6kVn9+n7pvx1PDABzcOMD5A6IgjhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:09:05.591231Z"},"content_sha256":"8a7477317bb032942c949e3211817ce93e56bf4e0400d77efe5b9ffdef57291e","schema_version":"1.0","event_id":"sha256:8a7477317bb032942c949e3211817ce93e56bf4e0400d77efe5b9ffdef57291e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H4Z3ZCDUT4BQJVWSQ2KFEADR7M/bundle.json","state_url":"https://pith.science/pith/H4Z3ZCDUT4BQJVWSQ2KFEADR7M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H4Z3ZCDUT4BQJVWSQ2KFEADR7M/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":"2026-05-29T21:09:05Z","links":{"resolver":"https://pith.science/pith/H4Z3ZCDUT4BQJVWSQ2KFEADR7M","bundle":"https://pith.science/pith/H4Z3ZCDUT4BQJVWSQ2KFEADR7M/bundle.json","state":"https://pith.science/pith/H4Z3ZCDUT4BQJVWSQ2KFEADR7M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H4Z3ZCDUT4BQJVWSQ2KFEADR7M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:H4Z3ZCDUT4BQJVWSQ2KFEADR7M","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":"990985eeffd8b668365b3825b70ffdba1ee304b202223ec89ea2a5f032206b9e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T15:15:23Z","title_canon_sha256":"82af8801b8bc169d2fc7a5229112decc9e79de3fb29e247eb3cfa7efc4fadf3e"},"schema_version":"1.0","source":{"id":"1810.04066","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04066","created_at":"2026-05-18T00:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04066v2","created_at":"2026-05-18T00:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04066","created_at":"2026-05-18T00:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"H4Z3ZCDUT4BQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H4Z3ZCDUT4BQJVWS","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H4Z3ZCDU","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:8a7477317bb032942c949e3211817ce93e56bf4e0400d77efe5b9ffdef57291e","target":"graph","created_at":"2026-05-18T00:03:23Z","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 a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks","authors_text":"Harri L\\\"ahdesm\\\"aki, Markus Heinonen, Pashupati Hegde, Samuel Kaski","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T15:15:23Z","title":"Deep learning with differential Gaussian process flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04066","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":"sha256:49d4252913c21c1e82f750e7b422e1fa4faf3af83d4ef469a069f4684b03584d","target":"record","created_at":"2026-05-18T00:03:23Z","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":"990985eeffd8b668365b3825b70ffdba1ee304b202223ec89ea2a5f032206b9e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T15:15:23Z","title_canon_sha256":"82af8801b8bc169d2fc7a5229112decc9e79de3fb29e247eb3cfa7efc4fadf3e"},"schema_version":"1.0","source":{"id":"1810.04066","kind":"arxiv","version":2}},"canonical_sha256":"3f33bc88749f0304d6d28694520071fb313f46095fef58a47364ff02416ac55f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f33bc88749f0304d6d28694520071fb313f46095fef58a47364ff02416ac55f","first_computed_at":"2026-05-18T00:03:23.933010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:23.933010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+eMLi7JkrYQ9Jgr/EEZOgvew6KVvxsb1EDZEO1Gs72Wi1nNCK+aK8qCdNJUYtmw3aeQ4sKM2O2GhHXVY5LpsCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:23.933657Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04066","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49d4252913c21c1e82f750e7b422e1fa4faf3af83d4ef469a069f4684b03584d","sha256:8a7477317bb032942c949e3211817ce93e56bf4e0400d77efe5b9ffdef57291e"],"state_sha256":"1f67b5690b90eccbc46ad68fe26bd0bee0ada31ed0046179257097f0a37c5989"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K0iXyoK89QEcLh5qNnEQKw6ZP3khEE+f5XiQHW7JLR9WB5xv+7oC+QFG1/sBFbowRZGUWbuKq5p+k1KYNRsgCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T21:09:05.594940Z","bundle_sha256":"6bcb5b19aec16967ed2716345acd1ff63b10520d127d1e80a6886afcbae53342"}}