{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZOV5ZOSVN2QEBDQRYLCJERY2Y3","short_pith_number":"pith:ZOV5ZOSV","canonical_record":{"source":{"id":"1804.00815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T04:05:00Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"784bc4d7e30faefda8021c4f47391145200e111ef0860b99fc91c85cf6fc515d","abstract_canon_sha256":"b2016f10ccbe21dfd03530db4437237261ea7e9a73d32dd62fbf1ac4a3ffe0cc"},"schema_version":"1.0"},"canonical_sha256":"cbabdcba556ea0408e11c2c492471ac6dc99428d5a13049139f119f0e765ff02","source":{"kind":"arxiv","id":"1804.00815","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.00815","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"arxiv_version","alias_value":"1804.00815v1","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00815","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZOV5ZOSVN2QE","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZOV5ZOSVN2QEBDQR","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZOV5ZOSV","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZOV5ZOSVN2QEBDQRYLCJERY2Y3","target":"record","payload":{"canonical_record":{"source":{"id":"1804.00815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T04:05:00Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"784bc4d7e30faefda8021c4f47391145200e111ef0860b99fc91c85cf6fc515d","abstract_canon_sha256":"b2016f10ccbe21dfd03530db4437237261ea7e9a73d32dd62fbf1ac4a3ffe0cc"},"schema_version":"1.0"},"canonical_sha256":"cbabdcba556ea0408e11c2c492471ac6dc99428d5a13049139f119f0e765ff02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:32.060905Z","signature_b64":"D8i6jVf7h9T4YzEbpzrosxnBLL1T7lQbQOGpBgPD1LQPITHv3XvDaczR0v9aZKykft5shGACRCBlh3BB7JJxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbabdcba556ea0408e11c2c492471ac6dc99428d5a13049139f119f0e765ff02","last_reissued_at":"2026-05-18T00:19:32.060124Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:32.060124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.00815","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":"2026-05-18T00:19:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qBYhMc3MUiyuQZHVuC586/t44LURvtgTlCX4mYRjUYWFPqDtCTbd1tFQ+mHxOcvq9Ss9WAWyUaJoM64BCvwfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:50:51.405879Z"},"content_sha256":"e997dd992a708181063534abb356600026c628f83e5d40a32d9dbb65d6801898","schema_version":"1.0","event_id":"sha256:e997dd992a708181063534abb356600026c628f83e5d40a32d9dbb65d6801898"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZOV5ZOSVN2QEBDQRYLCJERY2Y3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convolutional Neural Networks Regularized by Correlated Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bryan Tripp, Graham Taylor, Shamak Dutta","submitted_at":"2018-04-03T04:05:00Z","abstract_excerpt":"Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of correlated variability, we implement and evaluate correlated noise models in deep convolutional neural networks. Inspired by the cortex, correlation is defined as a function of the distance between neurons and their selectivity. We show how to sample from high-dimensional correlated distributions while keeping the procedure differentiable, so that back-propagation ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00815","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":"2026-05-18T00:19:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xw+BZTdGqnGLJZF/lwuNxJ68I4+NpGnzvolcRdKqfUj0jRa31Rac0i0gNi1V9oFGUGSh5Qm5zSTzdc+5KhthDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:50:51.406573Z"},"content_sha256":"cfbc3f30f5b3e3c6730985d24b5354e02cdbf0b811c2cbaa2d75cec9f972d4a1","schema_version":"1.0","event_id":"sha256:cfbc3f30f5b3e3c6730985d24b5354e02cdbf0b811c2cbaa2d75cec9f972d4a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZOV5ZOSVN2QEBDQRYLCJERY2Y3/bundle.json","state_url":"https://pith.science/pith/ZOV5ZOSVN2QEBDQRYLCJERY2Y3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZOV5ZOSVN2QEBDQRYLCJERY2Y3/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":"2026-06-12T02:50:51Z","links":{"resolver":"https://pith.science/pith/ZOV5ZOSVN2QEBDQRYLCJERY2Y3","bundle":"https://pith.science/pith/ZOV5ZOSVN2QEBDQRYLCJERY2Y3/bundle.json","state":"https://pith.science/pith/ZOV5ZOSVN2QEBDQRYLCJERY2Y3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZOV5ZOSVN2QEBDQRYLCJERY2Y3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZOV5ZOSVN2QEBDQRYLCJERY2Y3","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":"b2016f10ccbe21dfd03530db4437237261ea7e9a73d32dd62fbf1ac4a3ffe0cc","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T04:05:00Z","title_canon_sha256":"784bc4d7e30faefda8021c4f47391145200e111ef0860b99fc91c85cf6fc515d"},"schema_version":"1.0","source":{"id":"1804.00815","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.00815","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"arxiv_version","alias_value":"1804.00815v1","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00815","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZOV5ZOSVN2QE","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZOV5ZOSVN2QEBDQR","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZOV5ZOSV","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:cfbc3f30f5b3e3c6730985d24b5354e02cdbf0b811c2cbaa2d75cec9f972d4a1","target":"graph","created_at":"2026-05-18T00:19:32Z","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":"Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of correlated variability, we implement and evaluate correlated noise models in deep convolutional neural networks. Inspired by the cortex, correlation is defined as a function of the distance between neurons and their selectivity. We show how to sample from high-dimensional correlated distributions while keeping the procedure differentiable, so that back-propagation ca","authors_text":"Bryan Tripp, Graham Taylor, Shamak Dutta","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T04:05:00Z","title":"Convolutional Neural Networks Regularized by Correlated Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00815","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:e997dd992a708181063534abb356600026c628f83e5d40a32d9dbb65d6801898","target":"record","created_at":"2026-05-18T00:19:32Z","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":"b2016f10ccbe21dfd03530db4437237261ea7e9a73d32dd62fbf1ac4a3ffe0cc","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T04:05:00Z","title_canon_sha256":"784bc4d7e30faefda8021c4f47391145200e111ef0860b99fc91c85cf6fc515d"},"schema_version":"1.0","source":{"id":"1804.00815","kind":"arxiv","version":1}},"canonical_sha256":"cbabdcba556ea0408e11c2c492471ac6dc99428d5a13049139f119f0e765ff02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbabdcba556ea0408e11c2c492471ac6dc99428d5a13049139f119f0e765ff02","first_computed_at":"2026-05-18T00:19:32.060124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:32.060124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D8i6jVf7h9T4YzEbpzrosxnBLL1T7lQbQOGpBgPD1LQPITHv3XvDaczR0v9aZKykft5shGACRCBlh3BB7JJxBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:32.060905Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.00815","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e997dd992a708181063534abb356600026c628f83e5d40a32d9dbb65d6801898","sha256:cfbc3f30f5b3e3c6730985d24b5354e02cdbf0b811c2cbaa2d75cec9f972d4a1"],"state_sha256":"22ccd2b8ccf0e2844c4a644ff4418afe2f53f7d3391c6a16732325724b14035c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wxvy/jmfMd1thavK5bgMTaQUOzzFs7OTfo6OPaTyPdunZR0jxngDLQfDgq00Oeu3imkVZc1O4P51V4L+xZ1FAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T02:50:51.410867Z","bundle_sha256":"3c771a4518019a289a2ee542731e16a1e91b3bd4bdaecbdfa35f7b4af521a648"}}