{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YO7BF62EIBQ3VL5XBQQVHYRM2Q","short_pith_number":"pith:YO7BF62E","schema_version":"1.0","canonical_sha256":"c3be12fb444061baafb70c2153e22cd404a810404b9afec3ac2a9f720b2fdaff","source":{"kind":"arxiv","id":"1708.08487","version":2},"attestation_state":"computed","paper":{"title":"On denoising autoencoders trained to minimise binary cross-entropy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Anil A. Bharath, Antonia Creswell, Kai Arulkumaran","submitted_at":"2017-08-28T19:07:33Z","abstract_excerpt":"Denoising autoencoders (DAEs) are powerful deep learning models used for feature extraction, data generation and network pre-training. DAEs consist of an encoder and decoder which may be trained simultaneously to minimise a loss (function) between an input and the reconstruction of a corrupted version of the input. There are two common loss functions used for training autoencoders, these include the mean-squared error (MSE) and the binary cross-entropy (BCE). When training autoencoders on image data a natural choice of loss function is BCE, since pixel values may be normalised to take values i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1708.08487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-28T19:07:33Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f125452b1bdf5b1106f859f4a2f9a158172f906b99e7da1b97e3a45eb9831fc4","abstract_canon_sha256":"aeed222f9c1625f922cecc0a5c0aca3be72ba1a2e670f3e6f02c159c5ac01224"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:29.853234Z","signature_b64":"CcwrDK6lry0CG9dN541mToV1ZwAoeks3l/ye10npnpjcqEMlhkL4m1VljYnTZGk/xsPfbmOTc4c8/mTgCmpQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3be12fb444061baafb70c2153e22cd404a810404b9afec3ac2a9f720b2fdaff","last_reissued_at":"2026-05-18T00:33:29.852684Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:29.852684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On denoising autoencoders trained to minimise binary cross-entropy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Anil A. Bharath, Antonia Creswell, Kai Arulkumaran","submitted_at":"2017-08-28T19:07:33Z","abstract_excerpt":"Denoising autoencoders (DAEs) are powerful deep learning models used for feature extraction, data generation and network pre-training. DAEs consist of an encoder and decoder which may be trained simultaneously to minimise a loss (function) between an input and the reconstruction of a corrupted version of the input. There are two common loss functions used for training autoencoders, these include the mean-squared error (MSE) and the binary cross-entropy (BCE). When training autoencoders on image data a natural choice of loss function is BCE, since pixel values may be normalised to take values i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.08487","kind":"arxiv","version":2},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1708.08487","created_at":"2026-05-18T00:33:29.852768+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.08487v2","created_at":"2026-05-18T00:33:29.852768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.08487","created_at":"2026-05-18T00:33:29.852768+00:00"},{"alias_kind":"pith_short_12","alias_value":"YO7BF62EIBQ3","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YO7BF62EIBQ3VL5X","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YO7BF62E","created_at":"2026-05-18T12:31:56.362134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06582","citing_title":"AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YO7BF62EIBQ3VL5XBQQVHYRM2Q","json":"https://pith.science/pith/YO7BF62EIBQ3VL5XBQQVHYRM2Q.json","graph_json":"https://pith.science/api/pith-number/YO7BF62EIBQ3VL5XBQQVHYRM2Q/graph.json","events_json":"https://pith.science/api/pith-number/YO7BF62EIBQ3VL5XBQQVHYRM2Q/events.json","paper":"https://pith.science/paper/YO7BF62E"},"agent_actions":{"view_html":"https://pith.science/pith/YO7BF62EIBQ3VL5XBQQVHYRM2Q","download_json":"https://pith.science/pith/YO7BF62EIBQ3VL5XBQQVHYRM2Q.json","view_paper":"https://pith.science/paper/YO7BF62E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.08487&json=true","fetch_graph":"https://pith.science/api/pith-number/YO7BF62EIBQ3VL5XBQQVHYRM2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/YO7BF62EIBQ3VL5XBQQVHYRM2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YO7BF62EIBQ3VL5XBQQVHYRM2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YO7BF62EIBQ3VL5XBQQVHYRM2Q/action/storage_attestation","attest_author":"https://pith.science/pith/YO7BF62EIBQ3VL5XBQQVHYRM2Q/action/author_attestation","sign_citation":"https://pith.science/pith/YO7BF62EIBQ3VL5XBQQVHYRM2Q/action/citation_signature","submit_replication":"https://pith.science/pith/YO7BF62EIBQ3VL5XBQQVHYRM2Q/action/replication_record"}},"created_at":"2026-05-18T00:33:29.852768+00:00","updated_at":"2026-05-18T00:33:29.852768+00:00"}