{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:G7MOBMKLRHMLRM26U77VP2GX73","short_pith_number":"pith:G7MOBMKL","canonical_record":{"source":{"id":"1801.10437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-31T13:12:30Z","cross_cats_sorted":[],"title_canon_sha256":"482e016470de4254513b44f1d533596202c29ae1fc6a773ee1d11cd0a0f94033","abstract_canon_sha256":"b23a08532da5d669fdb8ed7c1f5bdca5b759a30847ce67c318d22a26cff5e82b"},"schema_version":"1.0"},"canonical_sha256":"37d8e0b14b89d8b8b35ea7ff57e8d7feef85e2a94180010723bd3786e0c2dc99","source":{"kind":"arxiv","id":"1801.10437","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.10437","created_at":"2026-05-18T00:24:40Z"},{"alias_kind":"arxiv_version","alias_value":"1801.10437v1","created_at":"2026-05-18T00:24:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.10437","created_at":"2026-05-18T00:24:40Z"},{"alias_kind":"pith_short_12","alias_value":"G7MOBMKLRHML","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G7MOBMKLRHMLRM26","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G7MOBMKL","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:G7MOBMKLRHMLRM26U77VP2GX73","target":"record","payload":{"canonical_record":{"source":{"id":"1801.10437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-31T13:12:30Z","cross_cats_sorted":[],"title_canon_sha256":"482e016470de4254513b44f1d533596202c29ae1fc6a773ee1d11cd0a0f94033","abstract_canon_sha256":"b23a08532da5d669fdb8ed7c1f5bdca5b759a30847ce67c318d22a26cff5e82b"},"schema_version":"1.0"},"canonical_sha256":"37d8e0b14b89d8b8b35ea7ff57e8d7feef85e2a94180010723bd3786e0c2dc99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:40.843533Z","signature_b64":"I9A+NXEMBe2juXICFGX6f7KBVzXZIc8fJh/MmOUIcqyFCIXVJSLt/WqoeEUETvHup/w3z2vEuZWPMAj1Tb6mCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37d8e0b14b89d8b8b35ea7ff57e8d7feef85e2a94180010723bd3786e0c2dc99","last_reissued_at":"2026-05-18T00:24:40.842882Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:40.842882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.10437","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":"2026-05-18T00:24:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q1ixPCfUgT1Ndx6gXmeGxv7r0gM9rsZb7mW2dxKdKU0fNJ0cfpanBT1F9eCMP1VwdeRAfHOHGt1OSVZauitbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T23:40:34.773076Z"},"content_sha256":"9c7cb47e70ae669d42c2672b7f1f7744ca0c3b365969ee2407bd3a7a62c8cc2c","schema_version":"1.0","event_id":"sha256:9c7cb47e70ae669d42c2672b7f1f7744ca0c3b365969ee2407bd3a7a62c8cc2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:G7MOBMKLRHMLRM26U77VP2GX73","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Learning Works in Practice. But Does it Work in Theory?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"L\\^e Nguy\\^en Hoang, Rachid Guerraoui","submitted_at":"2018-01-31T13:12:30Z","abstract_excerpt":"Deep learning relies on a very specific kind of neural networks: those superposing several neural layers. In the last few years, deep learning achieved major breakthroughs in many tasks such as image analysis, speech recognition, natural language processing, and so on. Yet, there is no theoretical explanation of this success. In particular, it is not clear why the deeper the network, the better it actually performs.\n  We argue that the explanation is intimately connected to a key feature of the data collected from our surrounding universe to feed the machine learning algorithms: large non-para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.10437","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":"2026-05-18T00:24:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8HpNUWPC/wE7JNlSsqYK8USglVyNqop+JFDuXNmcGqLAbCeqSq97fqfwbEf1u8YfinvBwfpttjH1YPfgFWtbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T23:40:34.773446Z"},"content_sha256":"aeaf64220b207ad5b3ce3ad83aac3d54f5cd4fe39c8cde5b8f9a1fbd607bd061","schema_version":"1.0","event_id":"sha256:aeaf64220b207ad5b3ce3ad83aac3d54f5cd4fe39c8cde5b8f9a1fbd607bd061"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7MOBMKLRHMLRM26U77VP2GX73/bundle.json","state_url":"https://pith.science/pith/G7MOBMKLRHMLRM26U77VP2GX73/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7MOBMKLRHMLRM26U77VP2GX73/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":"2026-06-22T23:40:34Z","links":{"resolver":"https://pith.science/pith/G7MOBMKLRHMLRM26U77VP2GX73","bundle":"https://pith.science/pith/G7MOBMKLRHMLRM26U77VP2GX73/bundle.json","state":"https://pith.science/pith/G7MOBMKLRHMLRM26U77VP2GX73/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7MOBMKLRHMLRM26U77VP2GX73/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:G7MOBMKLRHMLRM26U77VP2GX73","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":"b23a08532da5d669fdb8ed7c1f5bdca5b759a30847ce67c318d22a26cff5e82b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-31T13:12:30Z","title_canon_sha256":"482e016470de4254513b44f1d533596202c29ae1fc6a773ee1d11cd0a0f94033"},"schema_version":"1.0","source":{"id":"1801.10437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.10437","created_at":"2026-05-18T00:24:40Z"},{"alias_kind":"arxiv_version","alias_value":"1801.10437v1","created_at":"2026-05-18T00:24:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.10437","created_at":"2026-05-18T00:24:40Z"},{"alias_kind":"pith_short_12","alias_value":"G7MOBMKLRHML","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G7MOBMKLRHMLRM26","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G7MOBMKL","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:aeaf64220b207ad5b3ce3ad83aac3d54f5cd4fe39c8cde5b8f9a1fbd607bd061","target":"graph","created_at":"2026-05-18T00:24:40Z","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":"Deep learning relies on a very specific kind of neural networks: those superposing several neural layers. In the last few years, deep learning achieved major breakthroughs in many tasks such as image analysis, speech recognition, natural language processing, and so on. Yet, there is no theoretical explanation of this success. In particular, it is not clear why the deeper the network, the better it actually performs.\n  We argue that the explanation is intimately connected to a key feature of the data collected from our surrounding universe to feed the machine learning algorithms: large non-para","authors_text":"L\\^e Nguy\\^en Hoang, Rachid Guerraoui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-31T13:12:30Z","title":"Deep Learning Works in Practice. But Does it Work in Theory?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.10437","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":"sha256:9c7cb47e70ae669d42c2672b7f1f7744ca0c3b365969ee2407bd3a7a62c8cc2c","target":"record","created_at":"2026-05-18T00:24:40Z","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":"b23a08532da5d669fdb8ed7c1f5bdca5b759a30847ce67c318d22a26cff5e82b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-31T13:12:30Z","title_canon_sha256":"482e016470de4254513b44f1d533596202c29ae1fc6a773ee1d11cd0a0f94033"},"schema_version":"1.0","source":{"id":"1801.10437","kind":"arxiv","version":1}},"canonical_sha256":"37d8e0b14b89d8b8b35ea7ff57e8d7feef85e2a94180010723bd3786e0c2dc99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37d8e0b14b89d8b8b35ea7ff57e8d7feef85e2a94180010723bd3786e0c2dc99","first_computed_at":"2026-05-18T00:24:40.842882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:40.842882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I9A+NXEMBe2juXICFGX6f7KBVzXZIc8fJh/MmOUIcqyFCIXVJSLt/WqoeEUETvHup/w3z2vEuZWPMAj1Tb6mCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:40.843533Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.10437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c7cb47e70ae669d42c2672b7f1f7744ca0c3b365969ee2407bd3a7a62c8cc2c","sha256:aeaf64220b207ad5b3ce3ad83aac3d54f5cd4fe39c8cde5b8f9a1fbd607bd061"],"state_sha256":"7b1423de4bd64010c9a6e6a932b13d5edb8388da4e147c59b5ba1a139b67e893"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKTtkwOHftpUjl7/67jilA5MLJQ+lXEETFVNa1Z/1NM6u+BgkgUhQhaczi3FV33ENZdUrPXVaSLEaSTji4SCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T23:40:34.775490Z","bundle_sha256":"b791e4fe4d3100432a7ad43afe1adbcc086971ae698c04c015e16085239dbb1c"}}