{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:I57ETKO3SRZYOC4ANVO7FGLPHB","short_pith_number":"pith:I57ETKO3","schema_version":"1.0","canonical_sha256":"477e49a9db9473870b806d5df2996f3842fd4899b319c7204ee6c39d88a90e34","source":{"kind":"arxiv","id":"1507.05053","version":1},"attestation_state":"computed","paper":{"title":"Massively Deep Artificial Neural Networks for Handwritten Digit Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Keiron O'Shea","submitted_at":"2015-07-17T17:48:49Z","abstract_excerpt":"Greedy Restrictive Boltzmann Machines yield an fairly low 0.72% error rate on the famous MNIST database of handwritten digits. All that was required to achieve this result was a high number of hidden layers consisting of many neurons, and a graphics card to greatly speed up the rate of learning."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1507.05053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2015-07-17T17:48:49Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"f63990b13e5f5be09fc37cfcccaa9b2c28ab557ce1aabd12354de4e8df8d91e9","abstract_canon_sha256":"cb51274d6cdec9e6540bb3a6d76e9700ea7108c26ad24bfc0d7d122bebd52656"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:42.025607Z","signature_b64":"HoouJDMayJWD/bk9ZP+hLSUTvWcerR3G8KJj9IylyZCW0AAe/f/TY4BjUX4oIzhPu9QSpthlsusfoBTvtMd6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"477e49a9db9473870b806d5df2996f3842fd4899b319c7204ee6c39d88a90e34","last_reissued_at":"2026-05-18T01:36:42.024992Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:42.024992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively Deep Artificial Neural Networks for Handwritten Digit Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Keiron O'Shea","submitted_at":"2015-07-17T17:48:49Z","abstract_excerpt":"Greedy Restrictive Boltzmann Machines yield an fairly low 0.72% error rate on the famous MNIST database of handwritten digits. All that was required to achieve this result was a high number of hidden layers consisting of many neurons, and a graphics card to greatly speed up the rate of learning."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.05053","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1507.05053","created_at":"2026-05-18T01:36:42.025067+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.05053v1","created_at":"2026-05-18T01:36:42.025067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.05053","created_at":"2026-05-18T01:36:42.025067+00:00"},{"alias_kind":"pith_short_12","alias_value":"I57ETKO3SRZY","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"I57ETKO3SRZYOC4A","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"I57ETKO3","created_at":"2026-05-18T12:29:25.134429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I57ETKO3SRZYOC4ANVO7FGLPHB","json":"https://pith.science/pith/I57ETKO3SRZYOC4ANVO7FGLPHB.json","graph_json":"https://pith.science/api/pith-number/I57ETKO3SRZYOC4ANVO7FGLPHB/graph.json","events_json":"https://pith.science/api/pith-number/I57ETKO3SRZYOC4ANVO7FGLPHB/events.json","paper":"https://pith.science/paper/I57ETKO3"},"agent_actions":{"view_html":"https://pith.science/pith/I57ETKO3SRZYOC4ANVO7FGLPHB","download_json":"https://pith.science/pith/I57ETKO3SRZYOC4ANVO7FGLPHB.json","view_paper":"https://pith.science/paper/I57ETKO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.05053&json=true","fetch_graph":"https://pith.science/api/pith-number/I57ETKO3SRZYOC4ANVO7FGLPHB/graph.json","fetch_events":"https://pith.science/api/pith-number/I57ETKO3SRZYOC4ANVO7FGLPHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I57ETKO3SRZYOC4ANVO7FGLPHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I57ETKO3SRZYOC4ANVO7FGLPHB/action/storage_attestation","attest_author":"https://pith.science/pith/I57ETKO3SRZYOC4ANVO7FGLPHB/action/author_attestation","sign_citation":"https://pith.science/pith/I57ETKO3SRZYOC4ANVO7FGLPHB/action/citation_signature","submit_replication":"https://pith.science/pith/I57ETKO3SRZYOC4ANVO7FGLPHB/action/replication_record"}},"created_at":"2026-05-18T01:36:42.025067+00:00","updated_at":"2026-05-18T01:36:42.025067+00:00"}