{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CKIUGFRI4336ELNQTPLIBSP5DW","short_pith_number":"pith:CKIUGFRI","schema_version":"1.0","canonical_sha256":"1291431628e6f7e22db09bd680c9fd1da270c3ed3a172c377dc0f0fb12f67ea4","source":{"kind":"arxiv","id":"1806.01610","version":4},"attestation_state":"computed","paper":{"title":"Training Generative Reversible Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Patryk Chrab\\k{a}szcz, Robin Tibor Schirrmeister, Tonio Ball","submitted_at":"2018-06-05T11:16:42Z","abstract_excerpt":"Generative models with an encoding component such as autoencoders currently receive great interest. However, training of autoencoders is typically complicated by the need to train a separate encoder and decoder model that have to be enforced to be reciprocal to each other. To overcome this problem, by-design reversible neural networks (RevNets) had been previously used as generative models either directly optimizing the likelihood of the data under the model or using an adversarial approach on the generated data. Here, we instead investigate their performance using an adversary on the latent s"},"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":"1806.01610","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-05T11:16:42Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"1ff2ce7d88fd3f24fc6d24056839a0b729a2f7f8f87b5a324f27f5a49bce041d","abstract_canon_sha256":"0e1125aed1ae732c0e849235a78351587dfbad181881788c3d73ef728edcda4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:27.553510Z","signature_b64":"sTbvC+Qm7EGk/U1Ll8R3TOGh+7ZUR6fvlvw24ruZFnIm0eM4huolLe9HSVliKRTSGqw/4PuwJacygaIePmxnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1291431628e6f7e22db09bd680c9fd1da270c3ed3a172c377dc0f0fb12f67ea4","last_reissued_at":"2026-05-18T00:07:27.552853Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:27.552853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Generative Reversible Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Patryk Chrab\\k{a}szcz, Robin Tibor Schirrmeister, Tonio Ball","submitted_at":"2018-06-05T11:16:42Z","abstract_excerpt":"Generative models with an encoding component such as autoencoders currently receive great interest. However, training of autoencoders is typically complicated by the need to train a separate encoder and decoder model that have to be enforced to be reciprocal to each other. To overcome this problem, by-design reversible neural networks (RevNets) had been previously used as generative models either directly optimizing the likelihood of the data under the model or using an adversarial approach on the generated data. Here, we instead investigate their performance using an adversary on the latent s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01610","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1806.01610","created_at":"2026-05-18T00:07:27.552954+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01610v4","created_at":"2026-05-18T00:07:27.552954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01610","created_at":"2026-05-18T00:07:27.552954+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKIUGFRI4336","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKIUGFRI4336ELNQ","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKIUGFRI","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02392","citing_title":"Guided Image Generation with Conditional Invertible Neural Networks","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKIUGFRI4336ELNQTPLIBSP5DW","json":"https://pith.science/pith/CKIUGFRI4336ELNQTPLIBSP5DW.json","graph_json":"https://pith.science/api/pith-number/CKIUGFRI4336ELNQTPLIBSP5DW/graph.json","events_json":"https://pith.science/api/pith-number/CKIUGFRI4336ELNQTPLIBSP5DW/events.json","paper":"https://pith.science/paper/CKIUGFRI"},"agent_actions":{"view_html":"https://pith.science/pith/CKIUGFRI4336ELNQTPLIBSP5DW","download_json":"https://pith.science/pith/CKIUGFRI4336ELNQTPLIBSP5DW.json","view_paper":"https://pith.science/paper/CKIUGFRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01610&json=true","fetch_graph":"https://pith.science/api/pith-number/CKIUGFRI4336ELNQTPLIBSP5DW/graph.json","fetch_events":"https://pith.science/api/pith-number/CKIUGFRI4336ELNQTPLIBSP5DW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKIUGFRI4336ELNQTPLIBSP5DW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKIUGFRI4336ELNQTPLIBSP5DW/action/storage_attestation","attest_author":"https://pith.science/pith/CKIUGFRI4336ELNQTPLIBSP5DW/action/author_attestation","sign_citation":"https://pith.science/pith/CKIUGFRI4336ELNQTPLIBSP5DW/action/citation_signature","submit_replication":"https://pith.science/pith/CKIUGFRI4336ELNQTPLIBSP5DW/action/replication_record"}},"created_at":"2026-05-18T00:07:27.552954+00:00","updated_at":"2026-05-18T00:07:27.552954+00:00"}