{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C4Y36VNK74DWOX5MAH2SAUGW2N","short_pith_number":"pith:C4Y36VNK","schema_version":"1.0","canonical_sha256":"1731bf55aaff07675fac01f52050d6d354f8dee70079e0deca3fa66b00ad170f","source":{"kind":"arxiv","id":"2308.15613","version":3},"attestation_state":"computed","paper":{"title":"Mixed Variational Flows for Discrete Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.CO","authors_text":"Benjamin Bloem-Reddy, Gian Carlo Diluvi, Trevor Campbell","submitted_at":"2023-08-29T20:13:37Z","abstract_excerpt":"Variational flows allow practitioners to learn complex continuous distributions, but approximating discrete distributions remains a challenge. Current methodologies typically embed the discrete target in a continuous space - usually via continuous relaxation or dequantization - and then apply a continuous flow. These approaches involve a surrogate target that may not capture the original discrete target, might have biased or unstable gradients, and can create a difficult optimization problem. In this work, we develop a variational flow family for discrete distributions without any continuous e"},"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":"2308.15613","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2023-08-29T20:13:37Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"391d7130d3e9646123c79851f58b55144a11edb797936b1bfbb2407fad45b3c6","abstract_canon_sha256":"04a4797d9670d0729a34075835b772ab1694126ad94d31b90d8de0d4ecfe5325"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:13.516297Z","signature_b64":"1D+mE/fG6ak70YT1u/prJvTzFY//bAm1JlTbgOwkIs/wXXPZ5MT6GXH4SN1WJx+Q14kbN08GYqIwoXmiZDd6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1731bf55aaff07675fac01f52050d6d354f8dee70079e0deca3fa66b00ad170f","last_reissued_at":"2026-07-05T07:49:13.515774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:13.515774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixed Variational Flows for Discrete Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.CO","authors_text":"Benjamin Bloem-Reddy, Gian Carlo Diluvi, Trevor Campbell","submitted_at":"2023-08-29T20:13:37Z","abstract_excerpt":"Variational flows allow practitioners to learn complex continuous distributions, but approximating discrete distributions remains a challenge. Current methodologies typically embed the discrete target in a continuous space - usually via continuous relaxation or dequantization - and then apply a continuous flow. These approaches involve a surrogate target that may not capture the original discrete target, might have biased or unstable gradients, and can create a difficult optimization problem. In this work, we develop a variational flow family for discrete distributions without any continuous e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15613","kind":"arxiv","version":3},"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/2308.15613/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":"2308.15613","created_at":"2026-07-05T07:49:13.515831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15613v3","created_at":"2026-07-05T07:49:13.515831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15613","created_at":"2026-07-05T07:49:13.515831+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4Y36VNK74DW","created_at":"2026-07-05T07:49:13.515831+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4Y36VNK74DWOX5M","created_at":"2026-07-05T07:49:13.515831+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4Y36VNK","created_at":"2026-07-05T07:49:13.515831+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/C4Y36VNK74DWOX5MAH2SAUGW2N","json":"https://pith.science/pith/C4Y36VNK74DWOX5MAH2SAUGW2N.json","graph_json":"https://pith.science/api/pith-number/C4Y36VNK74DWOX5MAH2SAUGW2N/graph.json","events_json":"https://pith.science/api/pith-number/C4Y36VNK74DWOX5MAH2SAUGW2N/events.json","paper":"https://pith.science/paper/C4Y36VNK"},"agent_actions":{"view_html":"https://pith.science/pith/C4Y36VNK74DWOX5MAH2SAUGW2N","download_json":"https://pith.science/pith/C4Y36VNK74DWOX5MAH2SAUGW2N.json","view_paper":"https://pith.science/paper/C4Y36VNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15613&json=true","fetch_graph":"https://pith.science/api/pith-number/C4Y36VNK74DWOX5MAH2SAUGW2N/graph.json","fetch_events":"https://pith.science/api/pith-number/C4Y36VNK74DWOX5MAH2SAUGW2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4Y36VNK74DWOX5MAH2SAUGW2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4Y36VNK74DWOX5MAH2SAUGW2N/action/storage_attestation","attest_author":"https://pith.science/pith/C4Y36VNK74DWOX5MAH2SAUGW2N/action/author_attestation","sign_citation":"https://pith.science/pith/C4Y36VNK74DWOX5MAH2SAUGW2N/action/citation_signature","submit_replication":"https://pith.science/pith/C4Y36VNK74DWOX5MAH2SAUGW2N/action/replication_record"}},"created_at":"2026-07-05T07:49:13.515831+00:00","updated_at":"2026-07-05T07:49:13.515831+00:00"}