{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SXLX5LBSG2PEMYNXR5PH6LVEBE","short_pith_number":"pith:SXLX5LBS","schema_version":"1.0","canonical_sha256":"95d77eac32369e4661b78f5e7f2ea4091efb0f386c4b31817a69b30f32f2937e","source":{"kind":"arxiv","id":"2011.13704","version":2},"attestation_state":"computed","paper":{"title":"Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Enrico Guiraud, Jakob Drefs, J\\\"org L\\\"ucke","submitted_at":"2020-11-27T12:42:12Z","abstract_excerpt":"Discrete latent variables are considered important for real world data, which has motivated research on Variational Autoencoders (VAEs) with discrete latents. However, standard VAE training is not possible in this case, which has motivated different strategies to manipulate discrete distributions in order to train discrete VAEs similarly to conventional ones. Here we ask if it is also possible to keep the discrete nature of the latents fully intact by applying a direct discrete optimization for the encoding model. The approach is consequently strongly diverting from standard VAE-training by si"},"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":"2011.13704","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2020-11-27T12:42:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4ce6d65d6974c9e39262ae6b471db52ce60d80aa6054556418f6e3f734459468","abstract_canon_sha256":"bb5244ae91134ad8374dd13df479e9fc555157ef88d0fdee19ec0724e3c648ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:10.167420Z","signature_b64":"AKFtPbbtroJR40EllSjEWKGiK8cBRk+XwhMMdC9wm4E4Y7W3TSmmiLJRUZ5q4vPCacUCyn1ttQ0F7vmF2j8vCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d77eac32369e4661b78f5e7f2ea4091efb0f386c4b31817a69b30f32f2937e","last_reissued_at":"2026-07-05T05:54:10.166989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:10.166989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Enrico Guiraud, Jakob Drefs, J\\\"org L\\\"ucke","submitted_at":"2020-11-27T12:42:12Z","abstract_excerpt":"Discrete latent variables are considered important for real world data, which has motivated research on Variational Autoencoders (VAEs) with discrete latents. However, standard VAE training is not possible in this case, which has motivated different strategies to manipulate discrete distributions in order to train discrete VAEs similarly to conventional ones. Here we ask if it is also possible to keep the discrete nature of the latents fully intact by applying a direct discrete optimization for the encoding model. The approach is consequently strongly diverting from standard VAE-training by si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13704","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.13704/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2011.13704","created_at":"2026-07-05T05:54:10.167057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.13704v2","created_at":"2026-07-05T05:54:10.167057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13704","created_at":"2026-07-05T05:54:10.167057+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXLX5LBSG2PE","created_at":"2026-07-05T05:54:10.167057+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXLX5LBSG2PEMYNX","created_at":"2026-07-05T05:54:10.167057+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXLX5LBS","created_at":"2026-07-05T05:54:10.167057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SXLX5LBSG2PEMYNXR5PH6LVEBE","json":"https://pith.science/pith/SXLX5LBSG2PEMYNXR5PH6LVEBE.json","graph_json":"https://pith.science/api/pith-number/SXLX5LBSG2PEMYNXR5PH6LVEBE/graph.json","events_json":"https://pith.science/api/pith-number/SXLX5LBSG2PEMYNXR5PH6LVEBE/events.json","paper":"https://pith.science/paper/SXLX5LBS"},"agent_actions":{"view_html":"https://pith.science/pith/SXLX5LBSG2PEMYNXR5PH6LVEBE","download_json":"https://pith.science/pith/SXLX5LBSG2PEMYNXR5PH6LVEBE.json","view_paper":"https://pith.science/paper/SXLX5LBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.13704&json=true","fetch_graph":"https://pith.science/api/pith-number/SXLX5LBSG2PEMYNXR5PH6LVEBE/graph.json","fetch_events":"https://pith.science/api/pith-number/SXLX5LBSG2PEMYNXR5PH6LVEBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXLX5LBSG2PEMYNXR5PH6LVEBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXLX5LBSG2PEMYNXR5PH6LVEBE/action/storage_attestation","attest_author":"https://pith.science/pith/SXLX5LBSG2PEMYNXR5PH6LVEBE/action/author_attestation","sign_citation":"https://pith.science/pith/SXLX5LBSG2PEMYNXR5PH6LVEBE/action/citation_signature","submit_replication":"https://pith.science/pith/SXLX5LBSG2PEMYNXR5PH6LVEBE/action/replication_record"}},"created_at":"2026-07-05T05:54:10.167057+00:00","updated_at":"2026-07-05T05:54:10.167057+00:00"}