{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:IUZRCJH2KKNWM4IDPXWPXMXESG","short_pith_number":"pith:IUZRCJH2","schema_version":"1.0","canonical_sha256":"45331124fa529b6671037decfbb2e49193d1a509377c6b1258a0e30b3978e41a","source":{"kind":"arxiv","id":"1512.09300","version":2},"attestation_state":"computed","paper":{"title":"Autoencoding beyond pixels using a learned similarity metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Boesen Lindbo Larsen, Hugo Larochelle, Ole Winther, S{\\o}ren Kaae S{\\o}nderby","submitted_at":"2015-12-31T14:53:39Z","abstract_excerpt":"We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we replace element-wise errors with feature-wise errors to better capture the data distribution while offering invariance towards e.g. translation. We apply our method to images of faces and show that it outperforms VAEs with element-wise similarity measures in terms of visual fidelity. "},"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":"1512.09300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-31T14:53:39Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"95d1e1f82ad4ecf7bd589e6d53f9f0e3f8c5c0dc2ac1a540247bda29d1dac461","abstract_canon_sha256":"62b0f799132e7437448a0e1dc49009bfdd82d2ca04533425c0093866e66be5f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:58.709681Z","signature_b64":"LGltwGIJiAWEbzxiAqNIVVyMfMeHz10YUtFz2VBd+QRUQGDDNhYb5FBjoHs8z9eZGczq0SCW5Z/oE9XLmgAUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45331124fa529b6671037decfbb2e49193d1a509377c6b1258a0e30b3978e41a","last_reissued_at":"2026-05-18T01:20:58.709160Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:58.709160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoencoding beyond pixels using a learned similarity metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Boesen Lindbo Larsen, Hugo Larochelle, Ole Winther, S{\\o}ren Kaae S{\\o}nderby","submitted_at":"2015-12-31T14:53:39Z","abstract_excerpt":"We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we replace element-wise errors with feature-wise errors to better capture the data distribution while offering invariance towards e.g. translation. We apply our method to images of faces and show that it outperforms VAEs with element-wise similarity measures in terms of visual fidelity. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.09300","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":"1512.09300","created_at":"2026-05-18T01:20:58.709219+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.09300v2","created_at":"2026-05-18T01:20:58.709219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.09300","created_at":"2026-05-18T01:20:58.709219+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUZRCJH2KKNW","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUZRCJH2KKNWM4ID","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUZRCJH2","created_at":"2026-05-18T12:29:25.134429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"1605.08803","citing_title":"Density estimation using Real NVP","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUZRCJH2KKNWM4IDPXWPXMXESG","json":"https://pith.science/pith/IUZRCJH2KKNWM4IDPXWPXMXESG.json","graph_json":"https://pith.science/api/pith-number/IUZRCJH2KKNWM4IDPXWPXMXESG/graph.json","events_json":"https://pith.science/api/pith-number/IUZRCJH2KKNWM4IDPXWPXMXESG/events.json","paper":"https://pith.science/paper/IUZRCJH2"},"agent_actions":{"view_html":"https://pith.science/pith/IUZRCJH2KKNWM4IDPXWPXMXESG","download_json":"https://pith.science/pith/IUZRCJH2KKNWM4IDPXWPXMXESG.json","view_paper":"https://pith.science/paper/IUZRCJH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.09300&json=true","fetch_graph":"https://pith.science/api/pith-number/IUZRCJH2KKNWM4IDPXWPXMXESG/graph.json","fetch_events":"https://pith.science/api/pith-number/IUZRCJH2KKNWM4IDPXWPXMXESG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUZRCJH2KKNWM4IDPXWPXMXESG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUZRCJH2KKNWM4IDPXWPXMXESG/action/storage_attestation","attest_author":"https://pith.science/pith/IUZRCJH2KKNWM4IDPXWPXMXESG/action/author_attestation","sign_citation":"https://pith.science/pith/IUZRCJH2KKNWM4IDPXWPXMXESG/action/citation_signature","submit_replication":"https://pith.science/pith/IUZRCJH2KKNWM4IDPXWPXMXESG/action/replication_record"}},"created_at":"2026-05-18T01:20:58.709219+00:00","updated_at":"2026-05-18T01:20:58.709219+00:00"}