{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3QGJV6GMPWWJO2PLE43QQSDWE2","short_pith_number":"pith:3QGJV6GM","canonical_record":{"source":{"id":"1902.08959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-24T15:07:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e8b966078367f65f397a5df5426721d0fc399b20972683a55301438f97807371","abstract_canon_sha256":"562df90f99b8547fc1df4b3256e69aa51e7d63c66abe15926c5123ea220b0ba6"},"schema_version":"1.0"},"canonical_sha256":"dc0c9af8cc7dac9769eb27370848762684a76170f154717a420be877908255fa","source":{"kind":"arxiv","id":"1902.08959","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08959","created_at":"2026-05-17T23:52:47Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08959v1","created_at":"2026-05-17T23:52:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08959","created_at":"2026-05-17T23:52:47Z"},{"alias_kind":"pith_short_12","alias_value":"3QGJV6GMPWWJ","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3QGJV6GMPWWJO2PL","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3QGJV6GM","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3QGJV6GMPWWJO2PLE43QQSDWE2","target":"record","payload":{"canonical_record":{"source":{"id":"1902.08959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-24T15:07:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e8b966078367f65f397a5df5426721d0fc399b20972683a55301438f97807371","abstract_canon_sha256":"562df90f99b8547fc1df4b3256e69aa51e7d63c66abe15926c5123ea220b0ba6"},"schema_version":"1.0"},"canonical_sha256":"dc0c9af8cc7dac9769eb27370848762684a76170f154717a420be877908255fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:47.073622Z","signature_b64":"YSxO/2i4iASy0/5g/Guz90J1LgaDTax6guf/mDSPO6eOS2ArkPLtEmkMUIsg4i/4pLtG0NpFDztfRpzPFlNvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc0c9af8cc7dac9769eb27370848762684a76170f154717a420be877908255fa","last_reissued_at":"2026-05-17T23:52:47.072888Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:47.072888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.08959","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":"2026-05-17T23:52:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lR0uQXNhf3I5DSbg+5U+NATw5lsed+ewuHF+Ot4LZHanehc2OTlnY51l6mcAvToBiynbgSc1RS1WPJyypkjfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T12:42:51.102870Z"},"content_sha256":"e5875c091689decabe6e166fcc59baa62247b3e1c004906525d443d4aa299aa6","schema_version":"1.0","event_id":"sha256:e5875c091689decabe6e166fcc59baa62247b3e1c004906525d443d4aa299aa6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3QGJV6GMPWWJO2PLE43QQSDWE2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Formalization of The Natural Gradient Method for General Similarity Measures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aasa Feragen, Anton Mallasto, Tom Dela Haije","submitted_at":"2019-02-24T15:07:31Z","abstract_excerpt":"In optimization, the natural gradient method is well-known for likelihood maximization. The method uses the Kullback-Leibler divergence, corresponding infinitesimally to the Fisher-Rao metric, which is pulled back to the parameter space of a family of probability distributions. This way, gradients with respect to the parameters respect the Fisher-Rao geometry of the space of distributions, which might differ vastly from the standard Euclidean geometry of the parameter space, often leading to faster convergence. However, when minimizing an arbitrary similarity measure between distributions, it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08959","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":"2026-05-17T23:52:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e3O2LynHWe+BabnhamRChDKbLzY9yZpqjig2LIa796XDRY2bdLe+jmrTg3Dnnl8//Zfdl/uD+C1SXh0/9ekiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T12:42:51.103207Z"},"content_sha256":"8954e585b7a06676d9fa7bfa7ebf804f3870adb473207a4349f9903e4ee9e8d9","schema_version":"1.0","event_id":"sha256:8954e585b7a06676d9fa7bfa7ebf804f3870adb473207a4349f9903e4ee9e8d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3QGJV6GMPWWJO2PLE43QQSDWE2/bundle.json","state_url":"https://pith.science/pith/3QGJV6GMPWWJO2PLE43QQSDWE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3QGJV6GMPWWJO2PLE43QQSDWE2/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":"2026-06-07T12:42:51Z","links":{"resolver":"https://pith.science/pith/3QGJV6GMPWWJO2PLE43QQSDWE2","bundle":"https://pith.science/pith/3QGJV6GMPWWJO2PLE43QQSDWE2/bundle.json","state":"https://pith.science/pith/3QGJV6GMPWWJO2PLE43QQSDWE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3QGJV6GMPWWJO2PLE43QQSDWE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3QGJV6GMPWWJO2PLE43QQSDWE2","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":"562df90f99b8547fc1df4b3256e69aa51e7d63c66abe15926c5123ea220b0ba6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-24T15:07:31Z","title_canon_sha256":"e8b966078367f65f397a5df5426721d0fc399b20972683a55301438f97807371"},"schema_version":"1.0","source":{"id":"1902.08959","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08959","created_at":"2026-05-17T23:52:47Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08959v1","created_at":"2026-05-17T23:52:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08959","created_at":"2026-05-17T23:52:47Z"},{"alias_kind":"pith_short_12","alias_value":"3QGJV6GMPWWJ","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3QGJV6GMPWWJO2PL","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3QGJV6GM","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:8954e585b7a06676d9fa7bfa7ebf804f3870adb473207a4349f9903e4ee9e8d9","target":"graph","created_at":"2026-05-17T23:52:47Z","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 optimization, the natural gradient method is well-known for likelihood maximization. The method uses the Kullback-Leibler divergence, corresponding infinitesimally to the Fisher-Rao metric, which is pulled back to the parameter space of a family of probability distributions. This way, gradients with respect to the parameters respect the Fisher-Rao geometry of the space of distributions, which might differ vastly from the standard Euclidean geometry of the parameter space, often leading to faster convergence. However, when minimizing an arbitrary similarity measure between distributions, it ","authors_text":"Aasa Feragen, Anton Mallasto, Tom Dela Haije","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-24T15:07:31Z","title":"A Formalization of The Natural Gradient Method for General Similarity Measures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08959","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:e5875c091689decabe6e166fcc59baa62247b3e1c004906525d443d4aa299aa6","target":"record","created_at":"2026-05-17T23:52:47Z","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":"562df90f99b8547fc1df4b3256e69aa51e7d63c66abe15926c5123ea220b0ba6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-24T15:07:31Z","title_canon_sha256":"e8b966078367f65f397a5df5426721d0fc399b20972683a55301438f97807371"},"schema_version":"1.0","source":{"id":"1902.08959","kind":"arxiv","version":1}},"canonical_sha256":"dc0c9af8cc7dac9769eb27370848762684a76170f154717a420be877908255fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc0c9af8cc7dac9769eb27370848762684a76170f154717a420be877908255fa","first_computed_at":"2026-05-17T23:52:47.072888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:47.072888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YSxO/2i4iASy0/5g/Guz90J1LgaDTax6guf/mDSPO6eOS2ArkPLtEmkMUIsg4i/4pLtG0NpFDztfRpzPFlNvBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:47.073622Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.08959","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5875c091689decabe6e166fcc59baa62247b3e1c004906525d443d4aa299aa6","sha256:8954e585b7a06676d9fa7bfa7ebf804f3870adb473207a4349f9903e4ee9e8d9"],"state_sha256":"34950e3eb4785d4aa6d72893ab161101da12e0124f8ced1e8f1ec9d5226ad87d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ceq14CGrhzYnXKugb6wcQ0OC6ddHEhpgv8v1r4xmmUQWgcbz4wKJIJfUEVF1lTwWssFY+CRt0/gUoL2MoCGbAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T12:42:51.105962Z","bundle_sha256":"792b0965d7a9e10c363830d5316079af4ab281314d3a0871c3bf94a2be2a7bd1"}}