{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:63MYTV44TWDN6DL6N5D43NERKP","short_pith_number":"pith:63MYTV44","schema_version":"1.0","canonical_sha256":"f6d989d79c9d86df0d7e6f47cdb49153fb65b3a3362b97514a765600fd68cc1a","source":{"kind":"arxiv","id":"2505.18558","version":1},"attestation_state":"computed","paper":{"title":"Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Wenbo He, Zhijian Ou","submitted_at":"2025-05-24T06:52:23Z","abstract_excerpt":"Our examination of existing deep generative models (DGMs), including VAEs and GANs, reveals two problems. First, their capability in handling discrete observations and latent codes is unsatisfactory, though there are interesting efforts. Second, both VAEs and GANs optimize some criteria that are indirectly related to the data likelihood. To address these problems, we formally present Joint-stochastic-approximation (JSA) autoencoders - a new family of algorithms for building deep directed generative models, with application to semi-supervised learning. The JSA learning algorithm directly maximi"},"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":"2505.18558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T06:52:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7005e975a7081138b8e89e2b71a157961e76bf7610d6e7c3ebc080b04e26087d","abstract_canon_sha256":"46f75ac0ce2d29878e47c02451db894999ba3b97dd7c1b8c98c22450be8ff42a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:48.391842Z","signature_b64":"ze/NuBHzgnDILGq9m4ZfpOq7/pcyfiul2b7glC63uyZvH0x1PSJTZTUNec53YMe9nez0VrcSP8vTFQAimKJmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6d989d79c9d86df0d7e6f47cdb49153fb65b3a3362b97514a765600fd68cc1a","last_reissued_at":"2026-07-05T11:08:48.391300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:48.391300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Wenbo He, Zhijian Ou","submitted_at":"2025-05-24T06:52:23Z","abstract_excerpt":"Our examination of existing deep generative models (DGMs), including VAEs and GANs, reveals two problems. First, their capability in handling discrete observations and latent codes is unsatisfactory, though there are interesting efforts. Second, both VAEs and GANs optimize some criteria that are indirectly related to the data likelihood. To address these problems, we formally present Joint-stochastic-approximation (JSA) autoencoders - a new family of algorithms for building deep directed generative models, with application to semi-supervised learning. The JSA learning algorithm directly maximi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18558","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.18558/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":"2505.18558","created_at":"2026-07-05T11:08:48.391379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18558v1","created_at":"2026-07-05T11:08:48.391379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18558","created_at":"2026-07-05T11:08:48.391379+00:00"},{"alias_kind":"pith_short_12","alias_value":"63MYTV44TWDN","created_at":"2026-07-05T11:08:48.391379+00:00"},{"alias_kind":"pith_short_16","alias_value":"63MYTV44TWDN6DL6","created_at":"2026-07-05T11:08:48.391379+00:00"},{"alias_kind":"pith_short_8","alias_value":"63MYTV44","created_at":"2026-07-05T11:08:48.391379+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/63MYTV44TWDN6DL6N5D43NERKP","json":"https://pith.science/pith/63MYTV44TWDN6DL6N5D43NERKP.json","graph_json":"https://pith.science/api/pith-number/63MYTV44TWDN6DL6N5D43NERKP/graph.json","events_json":"https://pith.science/api/pith-number/63MYTV44TWDN6DL6N5D43NERKP/events.json","paper":"https://pith.science/paper/63MYTV44"},"agent_actions":{"view_html":"https://pith.science/pith/63MYTV44TWDN6DL6N5D43NERKP","download_json":"https://pith.science/pith/63MYTV44TWDN6DL6N5D43NERKP.json","view_paper":"https://pith.science/paper/63MYTV44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18558&json=true","fetch_graph":"https://pith.science/api/pith-number/63MYTV44TWDN6DL6N5D43NERKP/graph.json","fetch_events":"https://pith.science/api/pith-number/63MYTV44TWDN6DL6N5D43NERKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63MYTV44TWDN6DL6N5D43NERKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63MYTV44TWDN6DL6N5D43NERKP/action/storage_attestation","attest_author":"https://pith.science/pith/63MYTV44TWDN6DL6N5D43NERKP/action/author_attestation","sign_citation":"https://pith.science/pith/63MYTV44TWDN6DL6N5D43NERKP/action/citation_signature","submit_replication":"https://pith.science/pith/63MYTV44TWDN6DL6N5D43NERKP/action/replication_record"}},"created_at":"2026-07-05T11:08:48.391379+00:00","updated_at":"2026-07-05T11:08:48.391379+00:00"}