{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DPHVMIS5O45UBRKP5RT5A4B73Z","short_pith_number":"pith:DPHVMIS5","canonical_record":{"source":{"id":"1807.06630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-17T19:19:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3940bc9aa7bf7e2a50d0fc2e9f3a19dc281111014ffb31f76a00aa23fd3f22b7","abstract_canon_sha256":"fc0ad0ee90eac7be4374d33f70f31f93e2c2f53761465c9d34e6cd8dc1a69f25"},"schema_version":"1.0"},"canonical_sha256":"1bcf56225d773b40c54fec67d0703fde46efa63919f61fcf17c37cac37572dce","source":{"kind":"arxiv","id":"1807.06630","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06630","created_at":"2026-05-18T00:10:27Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06630v1","created_at":"2026-05-18T00:10:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06630","created_at":"2026-05-18T00:10:27Z"},{"alias_kind":"pith_short_12","alias_value":"DPHVMIS5O45U","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DPHVMIS5O45UBRKP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DPHVMIS5","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DPHVMIS5O45UBRKP5RT5A4B73Z","target":"record","payload":{"canonical_record":{"source":{"id":"1807.06630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-17T19:19:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3940bc9aa7bf7e2a50d0fc2e9f3a19dc281111014ffb31f76a00aa23fd3f22b7","abstract_canon_sha256":"fc0ad0ee90eac7be4374d33f70f31f93e2c2f53761465c9d34e6cd8dc1a69f25"},"schema_version":"1.0"},"canonical_sha256":"1bcf56225d773b40c54fec67d0703fde46efa63919f61fcf17c37cac37572dce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:27.366929Z","signature_b64":"ZayEZbkkN5MKfyw0OGotohNtxhHR9pHU5bFQUFMLred3MqUZvncDKQFTNNVnOXMDlFL1/nWBufDgknGSqEK4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bcf56225d773b40c54fec67d0703fde46efa63919f61fcf17c37cac37572dce","last_reissued_at":"2026-05-18T00:10:27.366354Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:27.366354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.06630","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":"2026-05-18T00:10:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J5lU5GCQ4IAELgfMmFkjx5hSC4Qdmy0tb2i8NmsCyQHqY9YgzTrv3dapaS0K+CUJY42eSy1H5DPpdFQEpF0VDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:10:51.229548Z"},"content_sha256":"ab10bda170d0f758ec77ba6c6e8806932c418e7b421190711967e09b6f20db5f","schema_version":"1.0","event_id":"sha256:ab10bda170d0f758ec77ba6c6e8806932c418e7b421190711967e09b6f20db5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DPHVMIS5O45UBRKP5RT5A4B73Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expressive power of outer product manifolds on feed-forward neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Bencz\\'ur, B\\'alint Dar\\'oczy, Rita Aleksziev","submitted_at":"2018-07-17T19:19:29Z","abstract_excerpt":"Hierarchical neural networks are exponentially more efficient than their corresponding \"shallow\" counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. Our main idea is to mathematically understand and describe the hierarchical structure of feedforward neural networks by reparametrization invariant Riemannian metrics. By computing or approximating the tangent subspace, we better utilize the original network via sparse representations that enables switching to shallow networks after a very early training stage. Our experiments "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06630","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":"2026-05-18T00:10:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AcVU2x6Xn0NtQu7/k1ZxbipbzMYoYRMPP5s3JzKPuW7Xma/EOQkN453PtUXmuvtO0BeRD/dlw8SyUVCN3wczCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:10:51.229885Z"},"content_sha256":"d30eb684d953ff8a679965774381ed0d5529dcde00c798597589737955b6aee7","schema_version":"1.0","event_id":"sha256:d30eb684d953ff8a679965774381ed0d5529dcde00c798597589737955b6aee7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPHVMIS5O45UBRKP5RT5A4B73Z/bundle.json","state_url":"https://pith.science/pith/DPHVMIS5O45UBRKP5RT5A4B73Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPHVMIS5O45UBRKP5RT5A4B73Z/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":"2026-06-29T18:10:51Z","links":{"resolver":"https://pith.science/pith/DPHVMIS5O45UBRKP5RT5A4B73Z","bundle":"https://pith.science/pith/DPHVMIS5O45UBRKP5RT5A4B73Z/bundle.json","state":"https://pith.science/pith/DPHVMIS5O45UBRKP5RT5A4B73Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPHVMIS5O45UBRKP5RT5A4B73Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DPHVMIS5O45UBRKP5RT5A4B73Z","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":"fc0ad0ee90eac7be4374d33f70f31f93e2c2f53761465c9d34e6cd8dc1a69f25","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-17T19:19:29Z","title_canon_sha256":"3940bc9aa7bf7e2a50d0fc2e9f3a19dc281111014ffb31f76a00aa23fd3f22b7"},"schema_version":"1.0","source":{"id":"1807.06630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06630","created_at":"2026-05-18T00:10:27Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06630v1","created_at":"2026-05-18T00:10:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06630","created_at":"2026-05-18T00:10:27Z"},{"alias_kind":"pith_short_12","alias_value":"DPHVMIS5O45U","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DPHVMIS5O45UBRKP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DPHVMIS5","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:d30eb684d953ff8a679965774381ed0d5529dcde00c798597589737955b6aee7","target":"graph","created_at":"2026-05-18T00:10:27Z","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":"Hierarchical neural networks are exponentially more efficient than their corresponding \"shallow\" counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. Our main idea is to mathematically understand and describe the hierarchical structure of feedforward neural networks by reparametrization invariant Riemannian metrics. By computing or approximating the tangent subspace, we better utilize the original network via sparse representations that enables switching to shallow networks after a very early training stage. Our experiments ","authors_text":"Andr\\'as Bencz\\'ur, B\\'alint Dar\\'oczy, Rita Aleksziev","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-17T19:19:29Z","title":"Expressive power of outer product manifolds on feed-forward neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06630","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:ab10bda170d0f758ec77ba6c6e8806932c418e7b421190711967e09b6f20db5f","target":"record","created_at":"2026-05-18T00:10:27Z","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":"fc0ad0ee90eac7be4374d33f70f31f93e2c2f53761465c9d34e6cd8dc1a69f25","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-17T19:19:29Z","title_canon_sha256":"3940bc9aa7bf7e2a50d0fc2e9f3a19dc281111014ffb31f76a00aa23fd3f22b7"},"schema_version":"1.0","source":{"id":"1807.06630","kind":"arxiv","version":1}},"canonical_sha256":"1bcf56225d773b40c54fec67d0703fde46efa63919f61fcf17c37cac37572dce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bcf56225d773b40c54fec67d0703fde46efa63919f61fcf17c37cac37572dce","first_computed_at":"2026-05-18T00:10:27.366354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:27.366354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZayEZbkkN5MKfyw0OGotohNtxhHR9pHU5bFQUFMLred3MqUZvncDKQFTNNVnOXMDlFL1/nWBufDgknGSqEK4DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:27.366929Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.06630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab10bda170d0f758ec77ba6c6e8806932c418e7b421190711967e09b6f20db5f","sha256:d30eb684d953ff8a679965774381ed0d5529dcde00c798597589737955b6aee7"],"state_sha256":"fee1101761177a98b291f66d73ebac888beba765357fee8ed609a2d54f09a300"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kSd4a4IqV4RYylyNaJg8qGunQfBU+2l4GkFK0t2XSxNsxevYMh8tP+2NwN5eE7QQRKv1Z4S9nftCF3ks4AS2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T18:10:51.231889Z","bundle_sha256":"a813ad30bf8f2d2f9b904a087e9132b8d247e8c38ec87ef17127516a0961e14d"}}