{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RY2PQ2M6JSK6L52ESLK4YAZOJ3","short_pith_number":"pith:RY2PQ2M6","canonical_record":{"source":{"id":"1710.10784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T06:42:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"75ab9c20004e537568dae3344ccc3e4ea78cbb2d4c0d540eb80d3ad7b31bc987","abstract_canon_sha256":"bbf6c4ba16184d18c579088f19a818d34a536c68e94dcc7ec8ae8014ef76c7e8"},"schema_version":"1.0"},"canonical_sha256":"8e34f8699e4c95e5f74492d5cc032e4ef07cb6e852811d08eedc1bcf2f80b31a","source":{"kind":"arxiv","id":"1710.10784","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.10784","created_at":"2026-05-18T00:31:46Z"},{"alias_kind":"arxiv_version","alias_value":"1710.10784v1","created_at":"2026-05-18T00:31:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10784","created_at":"2026-05-18T00:31:46Z"},{"alias_kind":"pith_short_12","alias_value":"RY2PQ2M6JSK6","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"RY2PQ2M6JSK6L52E","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"RY2PQ2M6","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RY2PQ2M6JSK6L52ESLK4YAZOJ3","target":"record","payload":{"canonical_record":{"source":{"id":"1710.10784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T06:42:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"75ab9c20004e537568dae3344ccc3e4ea78cbb2d4c0d540eb80d3ad7b31bc987","abstract_canon_sha256":"bbf6c4ba16184d18c579088f19a818d34a536c68e94dcc7ec8ae8014ef76c7e8"},"schema_version":"1.0"},"canonical_sha256":"8e34f8699e4c95e5f74492d5cc032e4ef07cb6e852811d08eedc1bcf2f80b31a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:46.500104Z","signature_b64":"tYWsMoQ6yDh1tUy1x0FRYQMz1YWxqjdVuhTSsbpg84ThggpoYtNfsTYfUy+Pms/k55Ao/HEQrajeWd/7+9nADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e34f8699e4c95e5f74492d5cc032e4ef07cb6e852811d08eedc1bcf2f80b31a","last_reissued_at":"2026-05-18T00:31:46.499487Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:46.499487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.10784","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":"2026-05-18T00:31:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nvZ0tvrYkrwXR9LaplAajo0CcrBZbKDM5Tf5OY/303DEp3xNGec0rW8Nsn0F1UUV9pAXkgnL+19MpFvBc5LCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:39:53.579654Z"},"content_sha256":"1d74de6678a84c13ff1007582b50833fcd9f35611217f87922d45f6528b51da6","schema_version":"1.0","event_id":"sha256:1d74de6678a84c13ff1007582b50833fcd9f35611217f87922d45f6528b51da6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RY2PQ2M6JSK6L52ESLK4YAZOJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How deep learning works --The geometry of deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiasong Wu, Ling Zhou, Xiao Dong","submitted_at":"2017-10-30T06:42:23Z","abstract_excerpt":"Why and how that deep learning works well on different tasks remains a mystery from a theoretical perspective. In this paper we draw a geometric picture of the deep learning system by finding its analogies with two existing geometric structures, the geometry of quantum computations and the geometry of the diffeomorphic template matching. In this framework, we give the geometric structures of different deep learning systems including convolutional neural networks, residual networks, recursive neural networks, recurrent neural networks and the equilibrium prapagation framework. We can also analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10784","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":"2026-05-18T00:31:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/4kTIAS3mRlGqBz3dK9BbZL6d/CE6PS94t71GSTgFB0lzk5Ng7HLTXzjYdigtJC9U4xWBq5eZC7Hs2L04BYdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:39:53.580027Z"},"content_sha256":"a4cb85a704c12cd48a1a8f193c1eecee4d4ecc80c5fdfbc2aa633ba4ea9ee296","schema_version":"1.0","event_id":"sha256:a4cb85a704c12cd48a1a8f193c1eecee4d4ecc80c5fdfbc2aa633ba4ea9ee296"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RY2PQ2M6JSK6L52ESLK4YAZOJ3/bundle.json","state_url":"https://pith.science/pith/RY2PQ2M6JSK6L52ESLK4YAZOJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RY2PQ2M6JSK6L52ESLK4YAZOJ3/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":"2026-05-27T02:39:53Z","links":{"resolver":"https://pith.science/pith/RY2PQ2M6JSK6L52ESLK4YAZOJ3","bundle":"https://pith.science/pith/RY2PQ2M6JSK6L52ESLK4YAZOJ3/bundle.json","state":"https://pith.science/pith/RY2PQ2M6JSK6L52ESLK4YAZOJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RY2PQ2M6JSK6L52ESLK4YAZOJ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RY2PQ2M6JSK6L52ESLK4YAZOJ3","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":"bbf6c4ba16184d18c579088f19a818d34a536c68e94dcc7ec8ae8014ef76c7e8","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T06:42:23Z","title_canon_sha256":"75ab9c20004e537568dae3344ccc3e4ea78cbb2d4c0d540eb80d3ad7b31bc987"},"schema_version":"1.0","source":{"id":"1710.10784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.10784","created_at":"2026-05-18T00:31:46Z"},{"alias_kind":"arxiv_version","alias_value":"1710.10784v1","created_at":"2026-05-18T00:31:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10784","created_at":"2026-05-18T00:31:46Z"},{"alias_kind":"pith_short_12","alias_value":"RY2PQ2M6JSK6","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"RY2PQ2M6JSK6L52E","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"RY2PQ2M6","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:a4cb85a704c12cd48a1a8f193c1eecee4d4ecc80c5fdfbc2aa633ba4ea9ee296","target":"graph","created_at":"2026-05-18T00:31:46Z","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":"Why and how that deep learning works well on different tasks remains a mystery from a theoretical perspective. In this paper we draw a geometric picture of the deep learning system by finding its analogies with two existing geometric structures, the geometry of quantum computations and the geometry of the diffeomorphic template matching. In this framework, we give the geometric structures of different deep learning systems including convolutional neural networks, residual networks, recursive neural networks, recurrent neural networks and the equilibrium prapagation framework. We can also analy","authors_text":"Jiasong Wu, Ling Zhou, Xiao Dong","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T06:42:23Z","title":"How deep learning works --The geometry of deep learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10784","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":"sha256:1d74de6678a84c13ff1007582b50833fcd9f35611217f87922d45f6528b51da6","target":"record","created_at":"2026-05-18T00:31:46Z","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":"bbf6c4ba16184d18c579088f19a818d34a536c68e94dcc7ec8ae8014ef76c7e8","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T06:42:23Z","title_canon_sha256":"75ab9c20004e537568dae3344ccc3e4ea78cbb2d4c0d540eb80d3ad7b31bc987"},"schema_version":"1.0","source":{"id":"1710.10784","kind":"arxiv","version":1}},"canonical_sha256":"8e34f8699e4c95e5f74492d5cc032e4ef07cb6e852811d08eedc1bcf2f80b31a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e34f8699e4c95e5f74492d5cc032e4ef07cb6e852811d08eedc1bcf2f80b31a","first_computed_at":"2026-05-18T00:31:46.499487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:46.499487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tYWsMoQ6yDh1tUy1x0FRYQMz1YWxqjdVuhTSsbpg84ThggpoYtNfsTYfUy+Pms/k55Ao/HEQrajeWd/7+9nADg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:46.500104Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.10784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d74de6678a84c13ff1007582b50833fcd9f35611217f87922d45f6528b51da6","sha256:a4cb85a704c12cd48a1a8f193c1eecee4d4ecc80c5fdfbc2aa633ba4ea9ee296"],"state_sha256":"82c7fad0ac52987fc8049887fe62b71e6b8654b3ec49ac8a41dbef30ced63f7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5UdDXWOuSq7njzAxWNdysSjMc/B/l11ZkMhwv+C9UnwlBo+vIMuLY5FgHKmRoJmo2LXLP/O0v1o8PxYnuzBKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:39:53.583060Z","bundle_sha256":"e116aa9c89c1b2f428f42ecda2ff6987e75bda01e248560ea8b396a4d202d8d1"}}