{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:W2OYJIHABELKGQI4CWX7CDNOKA","short_pith_number":"pith:W2OYJIHA","canonical_record":{"source":{"id":"1611.09232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-28T16:42:11Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e7faef73d9094eb232b5bf153bf5e40bb322185289dbebf237a2fa6f69129464","abstract_canon_sha256":"35aa33df7ff59fb9c34bc205f5721ca44c40d0d44005bb4719ede69ebbc2d9b7"},"schema_version":"1.0"},"canonical_sha256":"b69d84a0e00916a3411c15aff10dae5008f01810862d19bcaf9cf2b10ac6905a","source":{"kind":"arxiv","id":"1611.09232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.09232","created_at":"2026-05-18T00:56:28Z"},{"alias_kind":"arxiv_version","alias_value":"1611.09232v1","created_at":"2026-05-18T00:56:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09232","created_at":"2026-05-18T00:56:28Z"},{"alias_kind":"pith_short_12","alias_value":"W2OYJIHABELK","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"W2OYJIHABELKGQI4","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"W2OYJIHA","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:W2OYJIHABELKGQI4CWX7CDNOKA","target":"record","payload":{"canonical_record":{"source":{"id":"1611.09232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-28T16:42:11Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e7faef73d9094eb232b5bf153bf5e40bb322185289dbebf237a2fa6f69129464","abstract_canon_sha256":"35aa33df7ff59fb9c34bc205f5721ca44c40d0d44005bb4719ede69ebbc2d9b7"},"schema_version":"1.0"},"canonical_sha256":"b69d84a0e00916a3411c15aff10dae5008f01810862d19bcaf9cf2b10ac6905a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:28.715881Z","signature_b64":"dyH53USGjakVTX/GNvfqGhLPAsqnDc+c/uMndKdL+TDJAVVuViHqC7/JyUxudxQ0LJiuY06dTfaifFP1TaH6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b69d84a0e00916a3411c15aff10dae5008f01810862d19bcaf9cf2b10ac6905a","last_reissued_at":"2026-05-18T00:56:28.714981Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:28.714981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.09232","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":"2026-05-18T00:56:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qMmEFI2WNbdb8d/nz3SHtUsKYTW2ptfz9/nRT+sRdM5jI+g8NlWtickyOttp5K4e6JeX7qARrGuhge+CtLNCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T00:54:52.306801Z"},"content_sha256":"e20af53c8126b442d3dafc4b58e2b867f5bd2ddaca26a82f29f68119f48b8e81","schema_version":"1.0","event_id":"sha256:e20af53c8126b442d3dafc4b58e2b867f5bd2ddaca26a82f29f68119f48b8e81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:W2OYJIHABELKGQI4CWX7CDNOKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Convolutional Auto-Encoding via Random Convexification and Frequency-Domain Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Dongmei Jiang, Hichem Sahli, Meshia C\\'edric Oveneke, Mitchel Aliosha-Perez, Yong Zhao","submitted_at":"2016-11-28T16:42:11Z","abstract_excerpt":"The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the reliance on huge amounts of labeled data and specialized hardware can be a limiting factor when approaching new applications. To help alleviating these limitations, we propose an efficient learning strategy for layer-wise unsupervised training of deep CNNs on conventional hardware in acceptable time. Our proposed strategy consists of randomly convexifying the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09232","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":"2026-05-18T00:56:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RExWKDf5VCf3CNkdMS257PUnTz+ZxQ5wmmPsrxoTO+FVh3g9HP2jT+cJC0PoB9XsnuhrQ2YWGNS38xvXThGHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T00:54:52.307154Z"},"content_sha256":"6702022a6a86841d9967f5b4b7b9eacbc39a834541d59a037e7799c7c259c830","schema_version":"1.0","event_id":"sha256:6702022a6a86841d9967f5b4b7b9eacbc39a834541d59a037e7799c7c259c830"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W2OYJIHABELKGQI4CWX7CDNOKA/bundle.json","state_url":"https://pith.science/pith/W2OYJIHABELKGQI4CWX7CDNOKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W2OYJIHABELKGQI4CWX7CDNOKA/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":"2026-05-23T00:54:52Z","links":{"resolver":"https://pith.science/pith/W2OYJIHABELKGQI4CWX7CDNOKA","bundle":"https://pith.science/pith/W2OYJIHABELKGQI4CWX7CDNOKA/bundle.json","state":"https://pith.science/pith/W2OYJIHABELKGQI4CWX7CDNOKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W2OYJIHABELKGQI4CWX7CDNOKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:W2OYJIHABELKGQI4CWX7CDNOKA","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":"35aa33df7ff59fb9c34bc205f5721ca44c40d0d44005bb4719ede69ebbc2d9b7","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-28T16:42:11Z","title_canon_sha256":"e7faef73d9094eb232b5bf153bf5e40bb322185289dbebf237a2fa6f69129464"},"schema_version":"1.0","source":{"id":"1611.09232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.09232","created_at":"2026-05-18T00:56:28Z"},{"alias_kind":"arxiv_version","alias_value":"1611.09232v1","created_at":"2026-05-18T00:56:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.09232","created_at":"2026-05-18T00:56:28Z"},{"alias_kind":"pith_short_12","alias_value":"W2OYJIHABELK","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"W2OYJIHABELKGQI4","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"W2OYJIHA","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:6702022a6a86841d9967f5b4b7b9eacbc39a834541d59a037e7799c7c259c830","target":"graph","created_at":"2026-05-18T00:56:28Z","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":"The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the reliance on huge amounts of labeled data and specialized hardware can be a limiting factor when approaching new applications. To help alleviating these limitations, we propose an efficient learning strategy for layer-wise unsupervised training of deep CNNs on conventional hardware in acceptable time. Our proposed strategy consists of randomly convexifying the","authors_text":"Dongmei Jiang, Hichem Sahli, Meshia C\\'edric Oveneke, Mitchel Aliosha-Perez, Yong Zhao","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-28T16:42:11Z","title":"Efficient Convolutional Auto-Encoding via Random Convexification and Frequency-Domain Minimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.09232","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:e20af53c8126b442d3dafc4b58e2b867f5bd2ddaca26a82f29f68119f48b8e81","target":"record","created_at":"2026-05-18T00:56:28Z","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":"35aa33df7ff59fb9c34bc205f5721ca44c40d0d44005bb4719ede69ebbc2d9b7","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-28T16:42:11Z","title_canon_sha256":"e7faef73d9094eb232b5bf153bf5e40bb322185289dbebf237a2fa6f69129464"},"schema_version":"1.0","source":{"id":"1611.09232","kind":"arxiv","version":1}},"canonical_sha256":"b69d84a0e00916a3411c15aff10dae5008f01810862d19bcaf9cf2b10ac6905a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b69d84a0e00916a3411c15aff10dae5008f01810862d19bcaf9cf2b10ac6905a","first_computed_at":"2026-05-18T00:56:28.714981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:28.714981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dyH53USGjakVTX/GNvfqGhLPAsqnDc+c/uMndKdL+TDJAVVuViHqC7/JyUxudxQ0LJiuY06dTfaifFP1TaH6Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:28.715881Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.09232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e20af53c8126b442d3dafc4b58e2b867f5bd2ddaca26a82f29f68119f48b8e81","sha256:6702022a6a86841d9967f5b4b7b9eacbc39a834541d59a037e7799c7c259c830"],"state_sha256":"8779f43cf4c19a32914d7d4ff84fbf4b2b5f367556e34ebd5c3d18dff71dc5e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/snqnYYIsMVo4qADsjZhdQQrbYrBMFQ9EHU7K3t12vZQgrQIhqXm6IHfI82/EpnDlkwzHq1nPvz+LOMn2PYCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T00:54:52.310616Z","bundle_sha256":"7d21e9294631772462fca3bb81daecd3c6fe0cc15cfa0750eb686f0ff9475ad1"}}