{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:HMM5UZXNJY6ZXBGCFCISSZOHVD","short_pith_number":"pith:HMM5UZXN","schema_version":"1.0","canonical_sha256":"3b19da66ed4e3d9b84c228912965c7a8c00ab40b022ead8a3c1d25d5f2a6711d","source":{"kind":"arxiv","id":"1412.6597","version":4},"attestation_state":"computed","paper":{"title":"An Analysis of Unsupervised Pre-training in Light of Recent Advances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Pooya Khorrami, Thomas S. Huang, Tom Le Paine, Wei Han","submitted_at":"2014-12-20T04:20:55Z","abstract_excerpt":"Convolutional neural networks perform well on object recognition because of a number of recent advances: rectified linear units (ReLUs), data augmentation, dropout, and large labelled datasets. Unsupervised data has been proposed as another way to improve performance. Unfortunately, unsupervised pre-training is not used by state-of-the-art methods leading to the following question: Is unsupervised pre-training still useful given recent advances? If so, when? We answer this in three parts: we 1) develop an unsupervised method that incorporates ReLUs and recent unsupervised regularization techni"},"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":"1412.6597","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-20T04:20:55Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"b399eb07ac04bdcccac2b1436e288800a9be8422e2602e5dcd81fc6eab6ff2b4","abstract_canon_sha256":"ffac366ea501edb8cd3d55c5e904bea14b2bf6ce678d14531ef407d1fdca8719"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:00.644087Z","signature_b64":"g1HQ4eZk1+2meSElW3M6SIFaE3kvXtFYsuFF97JdGJPKyKcSb7BAOEc4RbcxcAP4Fx2EPJzNBemncw1tGP5oCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b19da66ed4e3d9b84c228912965c7a8c00ab40b022ead8a3c1d25d5f2a6711d","last_reissued_at":"2026-05-18T02:19:00.643407Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:00.643407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Analysis of Unsupervised Pre-training in Light of Recent Advances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Pooya Khorrami, Thomas S. Huang, Tom Le Paine, Wei Han","submitted_at":"2014-12-20T04:20:55Z","abstract_excerpt":"Convolutional neural networks perform well on object recognition because of a number of recent advances: rectified linear units (ReLUs), data augmentation, dropout, and large labelled datasets. Unsupervised data has been proposed as another way to improve performance. Unfortunately, unsupervised pre-training is not used by state-of-the-art methods leading to the following question: Is unsupervised pre-training still useful given recent advances? If so, when? We answer this in three parts: we 1) develop an unsupervised method that incorporates ReLUs and recent unsupervised regularization techni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6597","kind":"arxiv","version":4},"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":"1412.6597","created_at":"2026-05-18T02:19:00.643520+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.6597v4","created_at":"2026-05-18T02:19:00.643520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6597","created_at":"2026-05-18T02:19:00.643520+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMM5UZXNJY6Z","created_at":"2026-05-18T12:28:30.664211+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMM5UZXNJY6ZXBGC","created_at":"2026-05-18T12:28:30.664211+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMM5UZXN","created_at":"2026-05-18T12:28:30.664211+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/HMM5UZXNJY6ZXBGCFCISSZOHVD","json":"https://pith.science/pith/HMM5UZXNJY6ZXBGCFCISSZOHVD.json","graph_json":"https://pith.science/api/pith-number/HMM5UZXNJY6ZXBGCFCISSZOHVD/graph.json","events_json":"https://pith.science/api/pith-number/HMM5UZXNJY6ZXBGCFCISSZOHVD/events.json","paper":"https://pith.science/paper/HMM5UZXN"},"agent_actions":{"view_html":"https://pith.science/pith/HMM5UZXNJY6ZXBGCFCISSZOHVD","download_json":"https://pith.science/pith/HMM5UZXNJY6ZXBGCFCISSZOHVD.json","view_paper":"https://pith.science/paper/HMM5UZXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.6597&json=true","fetch_graph":"https://pith.science/api/pith-number/HMM5UZXNJY6ZXBGCFCISSZOHVD/graph.json","fetch_events":"https://pith.science/api/pith-number/HMM5UZXNJY6ZXBGCFCISSZOHVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMM5UZXNJY6ZXBGCFCISSZOHVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMM5UZXNJY6ZXBGCFCISSZOHVD/action/storage_attestation","attest_author":"https://pith.science/pith/HMM5UZXNJY6ZXBGCFCISSZOHVD/action/author_attestation","sign_citation":"https://pith.science/pith/HMM5UZXNJY6ZXBGCFCISSZOHVD/action/citation_signature","submit_replication":"https://pith.science/pith/HMM5UZXNJY6ZXBGCFCISSZOHVD/action/replication_record"}},"created_at":"2026-05-18T02:19:00.643520+00:00","updated_at":"2026-05-18T02:19:00.643520+00:00"}