{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:EWCNC7WWCSVRFTKG6S27LD4IPP","short_pith_number":"pith:EWCNC7WW","canonical_record":{"source":{"id":"1907.10935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T09:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"0056c7efdd8c4ba90c6e30ed5fd87f167fad76d60b44e53ef80450d4015310dd","abstract_canon_sha256":"2618606f84c0b34f9dabbae225926497943e570221454a4d39bc87e5b996e7eb"},"schema_version":"1.0"},"canonical_sha256":"2584d17ed614ab12cd46f4b5f58f887bdf528ce25706211fd7bf6ff918be6c43","source":{"kind":"arxiv","id":"1907.10935","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10935","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10935v1","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10935","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"EWCNC7WWCSVR","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EWCNC7WWCSVRFTKG","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EWCNC7WW","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:EWCNC7WWCSVRFTKG6S27LD4IPP","target":"record","payload":{"canonical_record":{"source":{"id":"1907.10935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T09:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"0056c7efdd8c4ba90c6e30ed5fd87f167fad76d60b44e53ef80450d4015310dd","abstract_canon_sha256":"2618606f84c0b34f9dabbae225926497943e570221454a4d39bc87e5b996e7eb"},"schema_version":"1.0"},"canonical_sha256":"2584d17ed614ab12cd46f4b5f58f887bdf528ce25706211fd7bf6ff918be6c43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:34.012561Z","signature_b64":"EWNKLFaHzcn01MT5HL69+pCM/JHlTM7chCXYzcZ7udVoBUahWwwqtOK8oRTckuhYpZ3jNmua/VChTlJhx+ELBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2584d17ed614ab12cd46f4b5f58f887bdf528ce25706211fd7bf6ff918be6c43","last_reissued_at":"2026-05-17T23:39:34.011929Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:34.011929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.10935","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":"2026-05-17T23:39:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e1Wh04lmdg/Zimx3HrjrEsfQpCNTS9qIP5qNx/XX3uGbw/2F44RCpxOpqmYGc+nzOkh9TlCpUOZLPRXxWLjyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:36:58.684280Z"},"content_sha256":"b87e4cc52827f3fb27b6a8ec78e0941cf75119c20c9e588a62e629eae1ece41d","schema_version":"1.0","event_id":"sha256:b87e4cc52827f3fb27b6a8ec78e0941cf75119c20c9e588a62e629eae1ece41d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:EWCNC7WWCSVRFTKG6S27LD4IPP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convolutional Neural Networks on Randomized Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cristian Ivan","submitted_at":"2019-07-25T09:59:27Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) are build specifically for computer vision tasks for which it is known that the input data is a hierarchical structure based on locally correlated elements. The question that naturally arises is what happens with the performance of CNNs if one of the basic properties of the data is removed, e.g. what happens if the image pixels are randomly permuted? Intuitively one expects that the convolutional network performs poorly in these circumstances in contrast to a multilayer perceptron (MLPs) whose classification accuracy should not be affected by the pixel rand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10935","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":"2026-05-17T23:39:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z1V12ZrFp5/lUY4vW87JlysXW64V84NbgfItPbI2kOC7XtbwjwNhaLrpLFScwKbR7crOjCLv4ivc33OkWBXCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:36:58.684993Z"},"content_sha256":"f9ad034ffcc74956ed8d21f76f3eb4e3007859c2286ed72eed818c4f2b1f72f4","schema_version":"1.0","event_id":"sha256:f9ad034ffcc74956ed8d21f76f3eb4e3007859c2286ed72eed818c4f2b1f72f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWCNC7WWCSVRFTKG6S27LD4IPP/bundle.json","state_url":"https://pith.science/pith/EWCNC7WWCSVRFTKG6S27LD4IPP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWCNC7WWCSVRFTKG6S27LD4IPP/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":"2026-05-25T20:36:58Z","links":{"resolver":"https://pith.science/pith/EWCNC7WWCSVRFTKG6S27LD4IPP","bundle":"https://pith.science/pith/EWCNC7WWCSVRFTKG6S27LD4IPP/bundle.json","state":"https://pith.science/pith/EWCNC7WWCSVRFTKG6S27LD4IPP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWCNC7WWCSVRFTKG6S27LD4IPP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EWCNC7WWCSVRFTKG6S27LD4IPP","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":"2618606f84c0b34f9dabbae225926497943e570221454a4d39bc87e5b996e7eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T09:59:27Z","title_canon_sha256":"0056c7efdd8c4ba90c6e30ed5fd87f167fad76d60b44e53ef80450d4015310dd"},"schema_version":"1.0","source":{"id":"1907.10935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10935","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10935v1","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10935","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"EWCNC7WWCSVR","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EWCNC7WWCSVRFTKG","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EWCNC7WW","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:f9ad034ffcc74956ed8d21f76f3eb4e3007859c2286ed72eed818c4f2b1f72f4","target":"graph","created_at":"2026-05-17T23:39:34Z","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":"Convolutional Neural Networks (CNNs) are build specifically for computer vision tasks for which it is known that the input data is a hierarchical structure based on locally correlated elements. The question that naturally arises is what happens with the performance of CNNs if one of the basic properties of the data is removed, e.g. what happens if the image pixels are randomly permuted? Intuitively one expects that the convolutional network performs poorly in these circumstances in contrast to a multilayer perceptron (MLPs) whose classification accuracy should not be affected by the pixel rand","authors_text":"Cristian Ivan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T09:59:27Z","title":"Convolutional Neural Networks on Randomized Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10935","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:b87e4cc52827f3fb27b6a8ec78e0941cf75119c20c9e588a62e629eae1ece41d","target":"record","created_at":"2026-05-17T23:39:34Z","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":"2618606f84c0b34f9dabbae225926497943e570221454a4d39bc87e5b996e7eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T09:59:27Z","title_canon_sha256":"0056c7efdd8c4ba90c6e30ed5fd87f167fad76d60b44e53ef80450d4015310dd"},"schema_version":"1.0","source":{"id":"1907.10935","kind":"arxiv","version":1}},"canonical_sha256":"2584d17ed614ab12cd46f4b5f58f887bdf528ce25706211fd7bf6ff918be6c43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2584d17ed614ab12cd46f4b5f58f887bdf528ce25706211fd7bf6ff918be6c43","first_computed_at":"2026-05-17T23:39:34.011929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:34.011929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EWNKLFaHzcn01MT5HL69+pCM/JHlTM7chCXYzcZ7udVoBUahWwwqtOK8oRTckuhYpZ3jNmua/VChTlJhx+ELBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:34.012561Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.10935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b87e4cc52827f3fb27b6a8ec78e0941cf75119c20c9e588a62e629eae1ece41d","sha256:f9ad034ffcc74956ed8d21f76f3eb4e3007859c2286ed72eed818c4f2b1f72f4"],"state_sha256":"9b892d0fddad170ddea8a527a0a75f1408045e1bd601e639a642dbc1a3840a30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AojXnsVhzZzrMd/wcIySXvEyA+QsehGSGkDa7urL4HLOD3O+PoddoJoShE+Uq2FaW4fPIwh6rZKMuOl+AR0SCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:36:58.688592Z","bundle_sha256":"f2fae1a9f9e70a6b126b8328dda10882c2e567086073ce22c80711de4be46c84"}}