{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NKFB2MJULKMXMDR67YFH26TGIM","short_pith_number":"pith:NKFB2MJU","schema_version":"1.0","canonical_sha256":"6a8a1d31345a99760e3efe0a7d7a66433a73c9319e7033e5e2b9a58e32e7b9cf","source":{"kind":"arxiv","id":"1805.07349","version":2},"attestation_state":"computed","paper":{"title":"GumBolt: Extending Gumbel trick to Boltzmann priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir H. Khoshaman, Mohammad H. Amin","submitted_at":"2018-05-18T17:59:17Z","abstract_excerpt":"Boltzmann machines (BMs) are appealing candidates for powerful priors in variational autoencoders (VAEs), as they are capable of capturing nontrivial and multi-modal distributions over discrete variables. However, non-differentiability of the discrete units prohibits using the reparameterization trick, essential for low-noise back propagation. The Gumbel trick resolves this problem in a consistent way by relaxing the variables and distributions, but it is incompatible with BM priors. Here, we propose the GumBolt, a model that extends the Gumbel trick to BM priors in VAEs. GumBolt is significan"},"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":"1805.07349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T17:59:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bfbd2843fd36903024cf80b9b0fe44a82be39a945841cdc4cdd51f0c5001559b","abstract_canon_sha256":"f394d3588d76d845d015dbc5290b066531835c1ee39692ad385480e6e24cd246"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:24.410749Z","signature_b64":"cr/dD8Fd4qzg0pt0nXX3gxjCZWRf8XQCBaudi+RCQyqHRLAHi5HrlZ/PYcif1T89dBKwC3j3CKSK4DjjhlDjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a8a1d31345a99760e3efe0a7d7a66433a73c9319e7033e5e2b9a58e32e7b9cf","last_reissued_at":"2026-05-17T23:52:24.410247Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:24.410247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GumBolt: Extending Gumbel trick to Boltzmann priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir H. Khoshaman, Mohammad H. Amin","submitted_at":"2018-05-18T17:59:17Z","abstract_excerpt":"Boltzmann machines (BMs) are appealing candidates for powerful priors in variational autoencoders (VAEs), as they are capable of capturing nontrivial and multi-modal distributions over discrete variables. However, non-differentiability of the discrete units prohibits using the reparameterization trick, essential for low-noise back propagation. The Gumbel trick resolves this problem in a consistent way by relaxing the variables and distributions, but it is incompatible with BM priors. Here, we propose the GumBolt, a model that extends the Gumbel trick to BM priors in VAEs. GumBolt is significan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07349","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":"1805.07349","created_at":"2026-05-17T23:52:24.410332+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07349v2","created_at":"2026-05-17T23:52:24.410332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07349","created_at":"2026-05-17T23:52:24.410332+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKFB2MJULKMX","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKFB2MJULKMXMDR6","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKFB2MJU","created_at":"2026-05-18T12:32:40.477152+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/NKFB2MJULKMXMDR67YFH26TGIM","json":"https://pith.science/pith/NKFB2MJULKMXMDR67YFH26TGIM.json","graph_json":"https://pith.science/api/pith-number/NKFB2MJULKMXMDR67YFH26TGIM/graph.json","events_json":"https://pith.science/api/pith-number/NKFB2MJULKMXMDR67YFH26TGIM/events.json","paper":"https://pith.science/paper/NKFB2MJU"},"agent_actions":{"view_html":"https://pith.science/pith/NKFB2MJULKMXMDR67YFH26TGIM","download_json":"https://pith.science/pith/NKFB2MJULKMXMDR67YFH26TGIM.json","view_paper":"https://pith.science/paper/NKFB2MJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07349&json=true","fetch_graph":"https://pith.science/api/pith-number/NKFB2MJULKMXMDR67YFH26TGIM/graph.json","fetch_events":"https://pith.science/api/pith-number/NKFB2MJULKMXMDR67YFH26TGIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKFB2MJULKMXMDR67YFH26TGIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKFB2MJULKMXMDR67YFH26TGIM/action/storage_attestation","attest_author":"https://pith.science/pith/NKFB2MJULKMXMDR67YFH26TGIM/action/author_attestation","sign_citation":"https://pith.science/pith/NKFB2MJULKMXMDR67YFH26TGIM/action/citation_signature","submit_replication":"https://pith.science/pith/NKFB2MJULKMXMDR67YFH26TGIM/action/replication_record"}},"created_at":"2026-05-17T23:52:24.410332+00:00","updated_at":"2026-05-17T23:52:24.410332+00:00"}