{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:KWGEBX3TJSN5UALRRUJ7XRWAYX","short_pith_number":"pith:KWGEBX3T","canonical_record":{"source":{"id":"1511.06068","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T06:23:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f97cbb3f3c275b14e794174cf9c7fa8564367129f168b37172d398ab9cf0be0f","abstract_canon_sha256":"9ec9454116af1553bb66929edb1c8e1571ca2a06f9a84283dc36c4ac52f082bd"},"schema_version":"1.0"},"canonical_sha256":"558c40df734c9bda01718d13fbc6c0c5d032ae5b1055758487a629c59ec5f0ae","source":{"kind":"arxiv","id":"1511.06068","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06068","created_at":"2026-05-18T01:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06068v4","created_at":"2026-05-18T01:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06068","created_at":"2026-05-18T01:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"KWGEBX3TJSN5","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"KWGEBX3TJSN5UALR","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"KWGEBX3T","created_at":"2026-05-18T12:29:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:KWGEBX3TJSN5UALRRUJ7XRWAYX","target":"record","payload":{"canonical_record":{"source":{"id":"1511.06068","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T06:23:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f97cbb3f3c275b14e794174cf9c7fa8564367129f168b37172d398ab9cf0be0f","abstract_canon_sha256":"9ec9454116af1553bb66929edb1c8e1571ca2a06f9a84283dc36c4ac52f082bd"},"schema_version":"1.0"},"canonical_sha256":"558c40df734c9bda01718d13fbc6c0c5d032ae5b1055758487a629c59ec5f0ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:37.947723Z","signature_b64":"R2onLlDznPNzOkGsEdwlwSLDcCwxIAuYPg5mI2+yoJiu4ejwJhBXYTlWqv4Qr6HvPMcm42sgDD2y+YStXTfgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"558c40df734c9bda01718d13fbc6c0c5d032ae5b1055758487a629c59ec5f0ae","last_reissued_at":"2026-05-18T01:12:37.947029Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:37.947029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.06068","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BtKvEsp2BfWQzEdT0MoRkFqtZ3CVqbau+vEn9BqmHHPQubFSQzt5kHIII0RCPIxsHiyMAH9u7aKz1a3svwg9Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:24:42.350331Z"},"content_sha256":"a85b46708d8481ceda86f9032ba083ef7ad6d9be0a56a89a82f637c354ac10d3","schema_version":"1.0","event_id":"sha256:a85b46708d8481ceda86f9032ba083ef7ad6d9be0a56a89a82f637c354ac10d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:KWGEBX3TJSN5UALRRUJ7XRWAYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reducing Overfitting in Deep Networks by Decorrelating Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dhruv Batra, Faruk Ahmed, Larry Zitnick, Michael Cogswell, Ross Girshick","submitted_at":"2015-11-19T06:23:09Z","abstract_excerpt":"One major challenge in training Deep Neural Networks is preventing overfitting. Many techniques such as data augmentation and novel regularizers such as Dropout have been proposed to prevent overfitting without requiring a massive amount of training data. In this work, we propose a new regularizer called DeCov which leads to significantly reduced overfitting (as indicated by the difference between train and val performance), and better generalization. Our regularizer encourages diverse or non-redundant representations in Deep Neural Networks by minimizing the cross-covariance of hidden activat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06068","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjaA97MRml7OAJ9nhUgqgf7efKHpq4quX5VrJkicEmIc8hhrIrd+hAj/JQ6GmuJMsr1RLDN/VabkjEKVCcAnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:24:42.350989Z"},"content_sha256":"1d4b305aeb41fb5e43132c8e28e6e428f0c951d12196a2afa048bf124809d332","schema_version":"1.0","event_id":"sha256:1d4b305aeb41fb5e43132c8e28e6e428f0c951d12196a2afa048bf124809d332"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KWGEBX3TJSN5UALRRUJ7XRWAYX/bundle.json","state_url":"https://pith.science/pith/KWGEBX3TJSN5UALRRUJ7XRWAYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KWGEBX3TJSN5UALRRUJ7XRWAYX/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":"2026-05-25T19:24:42Z","links":{"resolver":"https://pith.science/pith/KWGEBX3TJSN5UALRRUJ7XRWAYX","bundle":"https://pith.science/pith/KWGEBX3TJSN5UALRRUJ7XRWAYX/bundle.json","state":"https://pith.science/pith/KWGEBX3TJSN5UALRRUJ7XRWAYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KWGEBX3TJSN5UALRRUJ7XRWAYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:KWGEBX3TJSN5UALRRUJ7XRWAYX","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":"9ec9454116af1553bb66929edb1c8e1571ca2a06f9a84283dc36c4ac52f082bd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T06:23:09Z","title_canon_sha256":"f97cbb3f3c275b14e794174cf9c7fa8564367129f168b37172d398ab9cf0be0f"},"schema_version":"1.0","source":{"id":"1511.06068","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06068","created_at":"2026-05-18T01:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06068v4","created_at":"2026-05-18T01:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06068","created_at":"2026-05-18T01:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"KWGEBX3TJSN5","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"KWGEBX3TJSN5UALR","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"KWGEBX3T","created_at":"2026-05-18T12:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:1d4b305aeb41fb5e43132c8e28e6e428f0c951d12196a2afa048bf124809d332","target":"graph","created_at":"2026-05-18T01:12:37Z","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":"One major challenge in training Deep Neural Networks is preventing overfitting. Many techniques such as data augmentation and novel regularizers such as Dropout have been proposed to prevent overfitting without requiring a massive amount of training data. In this work, we propose a new regularizer called DeCov which leads to significantly reduced overfitting (as indicated by the difference between train and val performance), and better generalization. Our regularizer encourages diverse or non-redundant representations in Deep Neural Networks by minimizing the cross-covariance of hidden activat","authors_text":"Dhruv Batra, Faruk Ahmed, Larry Zitnick, Michael Cogswell, Ross Girshick","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T06:23:09Z","title":"Reducing Overfitting in Deep Networks by Decorrelating Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06068","kind":"arxiv","version":4},"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:a85b46708d8481ceda86f9032ba083ef7ad6d9be0a56a89a82f637c354ac10d3","target":"record","created_at":"2026-05-18T01:12:37Z","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":"9ec9454116af1553bb66929edb1c8e1571ca2a06f9a84283dc36c4ac52f082bd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T06:23:09Z","title_canon_sha256":"f97cbb3f3c275b14e794174cf9c7fa8564367129f168b37172d398ab9cf0be0f"},"schema_version":"1.0","source":{"id":"1511.06068","kind":"arxiv","version":4}},"canonical_sha256":"558c40df734c9bda01718d13fbc6c0c5d032ae5b1055758487a629c59ec5f0ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"558c40df734c9bda01718d13fbc6c0c5d032ae5b1055758487a629c59ec5f0ae","first_computed_at":"2026-05-18T01:12:37.947029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:37.947029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R2onLlDznPNzOkGsEdwlwSLDcCwxIAuYPg5mI2+yoJiu4ejwJhBXYTlWqv4Qr6HvPMcm42sgDD2y+YStXTfgBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:37.947723Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.06068","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a85b46708d8481ceda86f9032ba083ef7ad6d9be0a56a89a82f637c354ac10d3","sha256:1d4b305aeb41fb5e43132c8e28e6e428f0c951d12196a2afa048bf124809d332"],"state_sha256":"24669016703d448456e32f7c7c4f383ca5f6c4bc0f0ef9f66e4d18f9f7a2816c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FylSELU+WopW5lD7d198OcnF43bzTPIYOcSeCCZWaxgsFT3V/K6TP87I6lZt2jPVACBHfkfnbm09tY2QBDI6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:24:42.354285Z","bundle_sha256":"92317f4b865f2efcbafefe9c5e348627723f6554c4079765119f65e03d776ef8"}}