{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:UTOXYSFG2QNELV6HQYZZEQELBA","short_pith_number":"pith:UTOXYSFG","canonical_record":{"source":{"id":"1606.04586","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-14T22:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"586ac2b8e8627574cbc039a952b7cdaf52d80d8c617d84710d8426f49854aa13","abstract_canon_sha256":"12a98de58839ffdd649124c58a81a98d2f23a3ec493a097658629396bf083ce1"},"schema_version":"1.0"},"canonical_sha256":"a4dd7c48a6d41a45d7c7863392408b0809f1301ea8eca8c056621195affecaa1","source":{"kind":"arxiv","id":"1606.04586","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.04586","created_at":"2026-05-18T01:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"1606.04586v1","created_at":"2026-05-18T01:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.04586","created_at":"2026-05-18T01:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"UTOXYSFG2QNE","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UTOXYSFG2QNELV6H","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UTOXYSFG","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:UTOXYSFG2QNELV6HQYZZEQELBA","target":"record","payload":{"canonical_record":{"source":{"id":"1606.04586","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-14T22:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"586ac2b8e8627574cbc039a952b7cdaf52d80d8c617d84710d8426f49854aa13","abstract_canon_sha256":"12a98de58839ffdd649124c58a81a98d2f23a3ec493a097658629396bf083ce1"},"schema_version":"1.0"},"canonical_sha256":"a4dd7c48a6d41a45d7c7863392408b0809f1301ea8eca8c056621195affecaa1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:24.748968Z","signature_b64":"2M4/HjNQCWvsmydzm2mNUU+hoGIz44i9oWXGRGZu6D84it33HEs6J1ecp0YOlS+V9oglTQf3EfXfBNgmFFc7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4dd7c48a6d41a45d7c7863392408b0809f1301ea8eca8c056621195affecaa1","last_reissued_at":"2026-05-18T01:12:24.748636Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:24.748636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.04586","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":"2026-05-18T01:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FcS35Uk8NXKXzec4VBLoI3h/10uRjFO+fY1xRui1Hchd3/IJ6aILD2foG973cJyKnDE4XlB/Pyf5LGcitdA/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:24:27.378674Z"},"content_sha256":"80a4fc443956be2281849a51e6fede046fd3722f02e4d2b2f941876501db87a1","schema_version":"1.0","event_id":"sha256:80a4fc443956be2281849a51e6fede046fd3722f02e4d2b2f941876501db87a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:UTOXYSFG2QNELV6HQYZZEQELBA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mehdi Sajjadi, Mehran Javanmardi, Tolga Tasdizen","submitted_at":"2016-06-14T22:30:08Z","abstract_excerpt":"Effective convolutional neural networks are trained on large sets of labeled data. However, creating large labeled datasets is a very costly and time-consuming task. Semi-supervised learning uses unlabeled data to train a model with higher accuracy when there is a limited set of labeled data available. In this paper, we consider the problem of semi-supervised learning with convolutional neural networks. Techniques such as randomized data augmentation, dropout and random max-pooling provide better generalization and stability for classifiers that are trained using gradient descent. Multiple pas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.04586","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":"2026-05-18T01:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IvrJqNWvenfQqk2h7RnkixPDh7//3ysyI5LH3XETZQQ0CnY9Voj610JmlGgBWyrKDI4aShIlmp46or7hKk/PAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:24:27.379529Z"},"content_sha256":"566e46327bd51fb1074f8b5c28b5d55293d0bcfe9fdc065bc9eaa8f1e605d3d3","schema_version":"1.0","event_id":"sha256:566e46327bd51fb1074f8b5c28b5d55293d0bcfe9fdc065bc9eaa8f1e605d3d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UTOXYSFG2QNELV6HQYZZEQELBA/bundle.json","state_url":"https://pith.science/pith/UTOXYSFG2QNELV6HQYZZEQELBA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UTOXYSFG2QNELV6HQYZZEQELBA/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":"2026-05-31T17:24:27Z","links":{"resolver":"https://pith.science/pith/UTOXYSFG2QNELV6HQYZZEQELBA","bundle":"https://pith.science/pith/UTOXYSFG2QNELV6HQYZZEQELBA/bundle.json","state":"https://pith.science/pith/UTOXYSFG2QNELV6HQYZZEQELBA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UTOXYSFG2QNELV6HQYZZEQELBA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:UTOXYSFG2QNELV6HQYZZEQELBA","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":"12a98de58839ffdd649124c58a81a98d2f23a3ec493a097658629396bf083ce1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-14T22:30:08Z","title_canon_sha256":"586ac2b8e8627574cbc039a952b7cdaf52d80d8c617d84710d8426f49854aa13"},"schema_version":"1.0","source":{"id":"1606.04586","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.04586","created_at":"2026-05-18T01:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"1606.04586v1","created_at":"2026-05-18T01:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.04586","created_at":"2026-05-18T01:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"UTOXYSFG2QNE","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UTOXYSFG2QNELV6H","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UTOXYSFG","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:566e46327bd51fb1074f8b5c28b5d55293d0bcfe9fdc065bc9eaa8f1e605d3d3","target":"graph","created_at":"2026-05-18T01:12:24Z","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":"Effective convolutional neural networks are trained on large sets of labeled data. However, creating large labeled datasets is a very costly and time-consuming task. Semi-supervised learning uses unlabeled data to train a model with higher accuracy when there is a limited set of labeled data available. In this paper, we consider the problem of semi-supervised learning with convolutional neural networks. Techniques such as randomized data augmentation, dropout and random max-pooling provide better generalization and stability for classifiers that are trained using gradient descent. Multiple pas","authors_text":"Mehdi Sajjadi, Mehran Javanmardi, Tolga Tasdizen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-14T22:30:08Z","title":"Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.04586","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":"sha256:80a4fc443956be2281849a51e6fede046fd3722f02e4d2b2f941876501db87a1","target":"record","created_at":"2026-05-18T01:12:24Z","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":"12a98de58839ffdd649124c58a81a98d2f23a3ec493a097658629396bf083ce1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-14T22:30:08Z","title_canon_sha256":"586ac2b8e8627574cbc039a952b7cdaf52d80d8c617d84710d8426f49854aa13"},"schema_version":"1.0","source":{"id":"1606.04586","kind":"arxiv","version":1}},"canonical_sha256":"a4dd7c48a6d41a45d7c7863392408b0809f1301ea8eca8c056621195affecaa1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4dd7c48a6d41a45d7c7863392408b0809f1301ea8eca8c056621195affecaa1","first_computed_at":"2026-05-18T01:12:24.748636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:24.748636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2M4/HjNQCWvsmydzm2mNUU+hoGIz44i9oWXGRGZu6D84it33HEs6J1ecp0YOlS+V9oglTQf3EfXfBNgmFFc7Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:24.748968Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.04586","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80a4fc443956be2281849a51e6fede046fd3722f02e4d2b2f941876501db87a1","sha256:566e46327bd51fb1074f8b5c28b5d55293d0bcfe9fdc065bc9eaa8f1e605d3d3"],"state_sha256":"47e93cfb19e2056a689b176d89151cab084edd27b3cbb28202411f4168cf2fa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+BKQFRM+P874SZMepH5bAupXbyQsMbTMLCLR1uRXeNgAfOdsVHqGUaaB2LbYlRifsmGxKQ6NjxpRIj6PJLPWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T17:24:27.384229Z","bundle_sha256":"05d06561399fbf30788e54e19a080a0037df258563cb6f6ec9adecb3f4593c4f"}}