{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:6B3UVPWLLDRDOAH2PPULN37Q6H","short_pith_number":"pith:6B3UVPWL","canonical_record":{"source":{"id":"1303.0818","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2013-03-04T20:41:09Z","cross_cats_sorted":["cs.IT","cs.LG","math.DG","math.IT"],"title_canon_sha256":"7b2aff46f2e1bc4bd4862a622b03d6506391dc413d8ac86fb3996e2cc5f22bcf","abstract_canon_sha256":"9768f0968867f569f99b673a33dcc46769df2943e75d3e8aa3db6d94f414c4f6"},"schema_version":"1.0"},"canonical_sha256":"f0774abecb58e23700fa7be8b6eff0f1e1537738a8764d92d296f0b526715ac1","source":{"kind":"arxiv","id":"1303.0818","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1303.0818","created_at":"2026-05-18T02:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"1303.0818v5","created_at":"2026-05-18T02:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1303.0818","created_at":"2026-05-18T02:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"6B3UVPWLLDRD","created_at":"2026-05-18T12:27:36Z"},{"alias_kind":"pith_short_16","alias_value":"6B3UVPWLLDRDOAH2","created_at":"2026-05-18T12:27:36Z"},{"alias_kind":"pith_short_8","alias_value":"6B3UVPWL","created_at":"2026-05-18T12:27:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:6B3UVPWLLDRDOAH2PPULN37Q6H","target":"record","payload":{"canonical_record":{"source":{"id":"1303.0818","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2013-03-04T20:41:09Z","cross_cats_sorted":["cs.IT","cs.LG","math.DG","math.IT"],"title_canon_sha256":"7b2aff46f2e1bc4bd4862a622b03d6506391dc413d8ac86fb3996e2cc5f22bcf","abstract_canon_sha256":"9768f0968867f569f99b673a33dcc46769df2943e75d3e8aa3db6d94f414c4f6"},"schema_version":"1.0"},"canonical_sha256":"f0774abecb58e23700fa7be8b6eff0f1e1537738a8764d92d296f0b526715ac1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:28:05.617707Z","signature_b64":"Cn6zQac10GRt6EdHkfCj1h8FwE0VWSWYzCt0oeBCDm23zO6kPndXVrGZGHaJYbALJ7uUKhIEso9nZPvljmuBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0774abecb58e23700fa7be8b6eff0f1e1537738a8764d92d296f0b526715ac1","last_reissued_at":"2026-05-18T02:28:05.617292Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:28:05.617292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1303.0818","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WG10NVjI9MIw/6HLQTFkI0msmeetzSevnslt6EvinHdolvhfwnmyyx8Tjx6e5c1ivAN1rZi8cHiVort2K6NEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:50:44.508319Z"},"content_sha256":"be00b8de1497b15ae59b890a27de3905f7f0031f443630b217207c9c99f8d6a1","schema_version":"1.0","event_id":"sha256:be00b8de1497b15ae59b890a27de3905f7f0031f443630b217207c9c99f8d6a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:6B3UVPWLLDRDOAH2PPULN37Q6H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Riemannian metrics for neural networks I: feedforward networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.DG","math.IT"],"primary_cat":"cs.NE","authors_text":"Yann Ollivier","submitted_at":"2013-03-04T20:41:09Z","abstract_excerpt":"We describe four algorithms for neural network training, each adapted to different scalability constraints. These algorithms are mathematically principled and invariant under a number of transformations in data and network representation, from which performance is thus independent. These algorithms are obtained from the setting of differential geometry, and are based on either the natural gradient using the Fisher information matrix, or on Hessian methods, scaled down in a specific way to allow for scalability while keeping some of their key mathematical properties."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1303.0818","kind":"arxiv","version":5},"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":"2026-05-18T02:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYmy19RXzMxQH5XAyO0xUzleUNeoy5z+4EeMffjWuTLM0AVI9bJmtsy/wBDRLQL+E8NGEpeRXHBSnGdr8P4OAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:50:44.509380Z"},"content_sha256":"82bb71d4b715d4ef56506b65e19080ce8d36f6a329717e89380f30f0aeaa935e","schema_version":"1.0","event_id":"sha256:82bb71d4b715d4ef56506b65e19080ce8d36f6a329717e89380f30f0aeaa935e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6B3UVPWLLDRDOAH2PPULN37Q6H/bundle.json","state_url":"https://pith.science/pith/6B3UVPWLLDRDOAH2PPULN37Q6H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6B3UVPWLLDRDOAH2PPULN37Q6H/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":"2026-08-13T05:50:44Z","links":{"resolver":"https://pith.science/pith/6B3UVPWLLDRDOAH2PPULN37Q6H","bundle":"https://pith.science/pith/6B3UVPWLLDRDOAH2PPULN37Q6H/bundle.json","state":"https://pith.science/pith/6B3UVPWLLDRDOAH2PPULN37Q6H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6B3UVPWLLDRDOAH2PPULN37Q6H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:6B3UVPWLLDRDOAH2PPULN37Q6H","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":"9768f0968867f569f99b673a33dcc46769df2943e75d3e8aa3db6d94f414c4f6","cross_cats_sorted":["cs.IT","cs.LG","math.DG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2013-03-04T20:41:09Z","title_canon_sha256":"7b2aff46f2e1bc4bd4862a622b03d6506391dc413d8ac86fb3996e2cc5f22bcf"},"schema_version":"1.0","source":{"id":"1303.0818","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1303.0818","created_at":"2026-05-18T02:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"1303.0818v5","created_at":"2026-05-18T02:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1303.0818","created_at":"2026-05-18T02:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"6B3UVPWLLDRD","created_at":"2026-05-18T12:27:36Z"},{"alias_kind":"pith_short_16","alias_value":"6B3UVPWLLDRDOAH2","created_at":"2026-05-18T12:27:36Z"},{"alias_kind":"pith_short_8","alias_value":"6B3UVPWL","created_at":"2026-05-18T12:27:36Z"}],"graph_snapshots":[{"event_id":"sha256:82bb71d4b715d4ef56506b65e19080ce8d36f6a329717e89380f30f0aeaa935e","target":"graph","created_at":"2026-05-18T02:28:05Z","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 describe four algorithms for neural network training, each adapted to different scalability constraints. These algorithms are mathematically principled and invariant under a number of transformations in data and network representation, from which performance is thus independent. These algorithms are obtained from the setting of differential geometry, and are based on either the natural gradient using the Fisher information matrix, or on Hessian methods, scaled down in a specific way to allow for scalability while keeping some of their key mathematical properties.","authors_text":"Yann Ollivier","cross_cats":["cs.IT","cs.LG","math.DG","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2013-03-04T20:41:09Z","title":"Riemannian metrics for neural networks I: feedforward networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1303.0818","kind":"arxiv","version":5},"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:be00b8de1497b15ae59b890a27de3905f7f0031f443630b217207c9c99f8d6a1","target":"record","created_at":"2026-05-18T02:28:05Z","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":"9768f0968867f569f99b673a33dcc46769df2943e75d3e8aa3db6d94f414c4f6","cross_cats_sorted":["cs.IT","cs.LG","math.DG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2013-03-04T20:41:09Z","title_canon_sha256":"7b2aff46f2e1bc4bd4862a622b03d6506391dc413d8ac86fb3996e2cc5f22bcf"},"schema_version":"1.0","source":{"id":"1303.0818","kind":"arxiv","version":5}},"canonical_sha256":"f0774abecb58e23700fa7be8b6eff0f1e1537738a8764d92d296f0b526715ac1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0774abecb58e23700fa7be8b6eff0f1e1537738a8764d92d296f0b526715ac1","first_computed_at":"2026-05-18T02:28:05.617292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:28:05.617292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cn6zQac10GRt6EdHkfCj1h8FwE0VWSWYzCt0oeBCDm23zO6kPndXVrGZGHaJYbALJ7uUKhIEso9nZPvljmuBBw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:28:05.617707Z","signed_message":"canonical_sha256_bytes"},"source_id":"1303.0818","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be00b8de1497b15ae59b890a27de3905f7f0031f443630b217207c9c99f8d6a1","sha256:82bb71d4b715d4ef56506b65e19080ce8d36f6a329717e89380f30f0aeaa935e"],"state_sha256":"160f556e5768f258d9237f72572fb44998c55baa9de69bcae761d8ac4b1a284b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIQgklXhUOmR3b27lEFMR8DnNl0TrH6BMcTTJcE0/o9PwYxm70/KkEE07PIFNfiohOlLKKm1qzrLjEaiIwfuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T05:50:44.517176Z","bundle_sha256":"1ba912da8a2dbae0c28d40dd710819eb108b7d7735ccdc8ef33034a481948ba4"}}