{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Z5MOORVOTVAVVJ7SIUWF2HUAC4","short_pith_number":"pith:Z5MOORVO","schema_version":"1.0","canonical_sha256":"cf58e746ae9d415aa7f2452c5d1e80170cf6f2710cafb44b88d89c5539543a71","source":{"kind":"arxiv","id":"1805.10958","version":1},"attestation_state":"computed","paper":{"title":"Discrete flow posteriors for variational inference in discrete dynamical systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Laurence Aitchison, Srinivas C. Turaga, Vincent Adam","submitted_at":"2018-05-28T14:56:26Z","abstract_excerpt":"Each training step for a variational autoencoder (VAE) requires us to sample from the approximate posterior, so we usually choose simple (e.g. factorised) approximate posteriors in which sampling is an efficient computation that fully exploits GPU parallelism. However, such simple approximate posteriors are often insufficient, as they eliminate statistical dependencies in the posterior. While it is possible to use normalizing flow approximate posteriors for continuous latents, some problems have discrete latents and strong statistical dependencies. The most natural approach to model these depe"},"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":"1805.10958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-28T14:56:26Z","cross_cats_sorted":["cs.LG","q-bio.NC"],"title_canon_sha256":"7d4e4e2320ec2e0af417adcf68040ff146058a201245368f61b21d8829f974f7","abstract_canon_sha256":"2525543f80eccb847f3f04c571a295a7ea24b53a687d5b4ffa5bcb674f0730a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:48.694507Z","signature_b64":"4WDidE39VybsJBrvwAkxyd+6o7C9u42+lvydWWhOma4ltlqcgguFidTJ2TZqQ1U5tvUrC8nmRzfRrt0Vo6GADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf58e746ae9d415aa7f2452c5d1e80170cf6f2710cafb44b88d89c5539543a71","last_reissued_at":"2026-05-18T00:14:48.693808Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:48.693808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete flow posteriors for variational inference in discrete dynamical systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Laurence Aitchison, Srinivas C. Turaga, Vincent Adam","submitted_at":"2018-05-28T14:56:26Z","abstract_excerpt":"Each training step for a variational autoencoder (VAE) requires us to sample from the approximate posterior, so we usually choose simple (e.g. factorised) approximate posteriors in which sampling is an efficient computation that fully exploits GPU parallelism. However, such simple approximate posteriors are often insufficient, as they eliminate statistical dependencies in the posterior. While it is possible to use normalizing flow approximate posteriors for continuous latents, some problems have discrete latents and strong statistical dependencies. The most natural approach to model these depe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10958","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1805.10958","created_at":"2026-05-18T00:14:48.693938+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10958v1","created_at":"2026-05-18T00:14:48.693938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10958","created_at":"2026-05-18T00:14:48.693938+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5MOORVOTVAV","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5MOORVOTVAVVJ7S","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5MOORVO","created_at":"2026-05-18T12:33:04.347982+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/Z5MOORVOTVAVVJ7SIUWF2HUAC4","json":"https://pith.science/pith/Z5MOORVOTVAVVJ7SIUWF2HUAC4.json","graph_json":"https://pith.science/api/pith-number/Z5MOORVOTVAVVJ7SIUWF2HUAC4/graph.json","events_json":"https://pith.science/api/pith-number/Z5MOORVOTVAVVJ7SIUWF2HUAC4/events.json","paper":"https://pith.science/paper/Z5MOORVO"},"agent_actions":{"view_html":"https://pith.science/pith/Z5MOORVOTVAVVJ7SIUWF2HUAC4","download_json":"https://pith.science/pith/Z5MOORVOTVAVVJ7SIUWF2HUAC4.json","view_paper":"https://pith.science/paper/Z5MOORVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10958&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5MOORVOTVAVVJ7SIUWF2HUAC4/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5MOORVOTVAVVJ7SIUWF2HUAC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5MOORVOTVAVVJ7SIUWF2HUAC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5MOORVOTVAVVJ7SIUWF2HUAC4/action/storage_attestation","attest_author":"https://pith.science/pith/Z5MOORVOTVAVVJ7SIUWF2HUAC4/action/author_attestation","sign_citation":"https://pith.science/pith/Z5MOORVOTVAVVJ7SIUWF2HUAC4/action/citation_signature","submit_replication":"https://pith.science/pith/Z5MOORVOTVAVVJ7SIUWF2HUAC4/action/replication_record"}},"created_at":"2026-05-18T00:14:48.693938+00:00","updated_at":"2026-05-18T00:14:48.693938+00:00"}