{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LQC4SAZEALP7FEK5NBCVALSPX3","short_pith_number":"pith:LQC4SAZE","canonical_record":{"source":{"id":"1807.03346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-07-09T19:15:30Z","cross_cats_sorted":[],"title_canon_sha256":"7cac27e6770986de8bcb43efdf4f59dd10e00c1345242625cd21c6c4b78eda4f","abstract_canon_sha256":"e2c985c1545a3b6d8b1a6bf98edd510ff51040348cc0881cecd635178a8a3d69"},"schema_version":"1.0"},"canonical_sha256":"5c05c9032402dff2915d6845502e4fbeecb47057283e1b649c259a8fbe6870ab","source":{"kind":"arxiv","id":"1807.03346","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03346","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03346v1","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03346","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"LQC4SAZEALP7","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LQC4SAZEALP7FEK5","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LQC4SAZE","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LQC4SAZEALP7FEK5NBCVALSPX3","target":"record","payload":{"canonical_record":{"source":{"id":"1807.03346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-07-09T19:15:30Z","cross_cats_sorted":[],"title_canon_sha256":"7cac27e6770986de8bcb43efdf4f59dd10e00c1345242625cd21c6c4b78eda4f","abstract_canon_sha256":"e2c985c1545a3b6d8b1a6bf98edd510ff51040348cc0881cecd635178a8a3d69"},"schema_version":"1.0"},"canonical_sha256":"5c05c9032402dff2915d6845502e4fbeecb47057283e1b649c259a8fbe6870ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:10.741084Z","signature_b64":"uBNJMdf5QWYJ3dsDBA3NyNgxsBnrJgqgIKgB89ucVbqpvc0t2HRlbmTJaGv79WzMIPn8jnQQPz8Pl4CLRmaeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c05c9032402dff2915d6845502e4fbeecb47057283e1b649c259a8fbe6870ab","last_reissued_at":"2026-05-18T00:11:10.740482Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:10.740482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.03346","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":"2026-05-18T00:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4JD7DbsvahRVuzNQS7Di41VGVdioQykoVzPGA4cC4wSDmoHn+7FtWdi23pfLabuldD5v2XDqAzdWZQhORCh3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T16:17:02.354429Z"},"content_sha256":"76fd9867d83bdb7786e39eea08feb1cc420fc785df887dd5cab44337789f6eeb","schema_version":"1.0","event_id":"sha256:76fd9867d83bdb7786e39eea08feb1cc420fc785df887dd5cab44337789f6eeb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LQC4SAZEALP7FEK5NBCVALSPX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Swarm Optimization To Enhance Autoencoders Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Maisa Doaud, Michael Mayo","submitted_at":"2018-07-09T19:15:30Z","abstract_excerpt":"Autoencoders learn data representations through reconstruction. Robust training is the key factor affecting the quality of the learned representations and, consequently, the accuracy of the application that use them. Previous works suggested methods for deciding the optimal autoencoder configuration which allows for robust training. Nevertheless, improving the accuracy of a trained autoencoder has got limited, if no, attention. We propose a new approach that improves the accuracy of a trained autoencoders results and answers the following question, Given a trained autoencoder, a test image, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03346","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":"2026-05-18T00:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W5Do6Aq31XROiA1nrY7JWE7HqSpTMQm6zxN75tPoP5Iw4E7xrmzLmm1QWiLQiK7ZkkAu6b9nliSh+h2/leQfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T16:17:02.354769Z"},"content_sha256":"6836fe7c1ed350e20f8d24637cbf7fcb9ea8a81f1801763b0b070c73735c2c7e","schema_version":"1.0","event_id":"sha256:6836fe7c1ed350e20f8d24637cbf7fcb9ea8a81f1801763b0b070c73735c2c7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQC4SAZEALP7FEK5NBCVALSPX3/bundle.json","state_url":"https://pith.science/pith/LQC4SAZEALP7FEK5NBCVALSPX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQC4SAZEALP7FEK5NBCVALSPX3/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":"2026-07-02T16:17:02Z","links":{"resolver":"https://pith.science/pith/LQC4SAZEALP7FEK5NBCVALSPX3","bundle":"https://pith.science/pith/LQC4SAZEALP7FEK5NBCVALSPX3/bundle.json","state":"https://pith.science/pith/LQC4SAZEALP7FEK5NBCVALSPX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQC4SAZEALP7FEK5NBCVALSPX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LQC4SAZEALP7FEK5NBCVALSPX3","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":"e2c985c1545a3b6d8b1a6bf98edd510ff51040348cc0881cecd635178a8a3d69","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-07-09T19:15:30Z","title_canon_sha256":"7cac27e6770986de8bcb43efdf4f59dd10e00c1345242625cd21c6c4b78eda4f"},"schema_version":"1.0","source":{"id":"1807.03346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03346","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03346v1","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03346","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"LQC4SAZEALP7","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LQC4SAZEALP7FEK5","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LQC4SAZE","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:6836fe7c1ed350e20f8d24637cbf7fcb9ea8a81f1801763b0b070c73735c2c7e","target":"graph","created_at":"2026-05-18T00:11:10Z","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":"Autoencoders learn data representations through reconstruction. Robust training is the key factor affecting the quality of the learned representations and, consequently, the accuracy of the application that use them. Previous works suggested methods for deciding the optimal autoencoder configuration which allows for robust training. Nevertheless, improving the accuracy of a trained autoencoder has got limited, if no, attention. We propose a new approach that improves the accuracy of a trained autoencoders results and answers the following question, Given a trained autoencoder, a test image, an","authors_text":"Maisa Doaud, Michael Mayo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-07-09T19:15:30Z","title":"Using Swarm Optimization To Enhance Autoencoders Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03346","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":"sha256:76fd9867d83bdb7786e39eea08feb1cc420fc785df887dd5cab44337789f6eeb","target":"record","created_at":"2026-05-18T00:11:10Z","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":"e2c985c1545a3b6d8b1a6bf98edd510ff51040348cc0881cecd635178a8a3d69","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-07-09T19:15:30Z","title_canon_sha256":"7cac27e6770986de8bcb43efdf4f59dd10e00c1345242625cd21c6c4b78eda4f"},"schema_version":"1.0","source":{"id":"1807.03346","kind":"arxiv","version":1}},"canonical_sha256":"5c05c9032402dff2915d6845502e4fbeecb47057283e1b649c259a8fbe6870ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c05c9032402dff2915d6845502e4fbeecb47057283e1b649c259a8fbe6870ab","first_computed_at":"2026-05-18T00:11:10.740482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:10.740482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uBNJMdf5QWYJ3dsDBA3NyNgxsBnrJgqgIKgB89ucVbqpvc0t2HRlbmTJaGv79WzMIPn8jnQQPz8Pl4CLRmaeAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:10.741084Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.03346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76fd9867d83bdb7786e39eea08feb1cc420fc785df887dd5cab44337789f6eeb","sha256:6836fe7c1ed350e20f8d24637cbf7fcb9ea8a81f1801763b0b070c73735c2c7e"],"state_sha256":"cde709b39523c4716749515038705a49adfe02ade0ee08a3cbf38a9aca6c4290"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QVgVh3szEl/k6/u6pjnZP0744ZyTUTF+qB+ZGXc1x4leAh0csRHMOq1cbOn674/kZ9eM3l5G9vVY4cvSklmRAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T16:17:02.356716Z","bundle_sha256":"05d1398f63e498d702eeaa2b1bb8f10d48aa7524f12b8b2b9d9726fa6eb55b43"}}