{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZXGOMZECRAYAUODTEPREHFT5PK","short_pith_number":"pith:ZXGOMZEC","schema_version":"1.0","canonical_sha256":"cdcce6648288300a387323e243967d7aaee8d63ccc89ed2f073e260d4b18159e","source":{"kind":"arxiv","id":"2607.01275","version":1},"attestation_state":"computed","paper":{"title":"eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Qijun Chen, Shaofan Li","submitted_at":"2026-06-30T23:05:06Z","abstract_excerpt":"Variational Autoencoders (VAEs) commonly assume a standard isotropic Gaussian prior over the latent space, an assumption that often fails to capture the true distribution of latent representations for complex datasets. This mismatch can limit reconstruction accuracy, reduce sample quality, and constrain the expressive power of the learned latent space. We propose the eXact-Prior Variational Autoencoder (X-VAE), a framework that replaces the conventional standard normal prior with a Gaussian prior derived from the latent representations of a pretrained autoencoder (AE). Specifically, the empiri"},"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":"2607.01275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-30T23:05:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2f49950ab7aa465f89f2e93015bebc3b1fdab89836a51ebecc4bb1a46cf17fc9","abstract_canon_sha256":"64006878c00110cc53ba55d6d9d4392209ea727caab059fca8f92f66214e61b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:16:56.028199Z","signature_b64":"dJw8ToKwy5JwH4p9FXRxDPJoGYNL+k2Lh0ISJCP+P0UHa8l3AOKsbpyuBAZJ+ViQzfLZ16TZ8BeTpFuxXRgoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdcce6648288300a387323e243967d7aaee8d63ccc89ed2f073e260d4b18159e","last_reissued_at":"2026-07-03T00:16:56.027786Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:16:56.027786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Qijun Chen, Shaofan Li","submitted_at":"2026-06-30T23:05:06Z","abstract_excerpt":"Variational Autoencoders (VAEs) commonly assume a standard isotropic Gaussian prior over the latent space, an assumption that often fails to capture the true distribution of latent representations for complex datasets. This mismatch can limit reconstruction accuracy, reduce sample quality, and constrain the expressive power of the learned latent space. We propose the eXact-Prior Variational Autoencoder (X-VAE), a framework that replaces the conventional standard normal prior with a Gaussian prior derived from the latent representations of a pretrained autoencoder (AE). Specifically, the empiri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01275","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/2607.01275/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":"2607.01275","created_at":"2026-07-03T00:16:56.027843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01275v1","created_at":"2026-07-03T00:16:56.027843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01275","created_at":"2026-07-03T00:16:56.027843+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXGOMZECRAYA","created_at":"2026-07-03T00:16:56.027843+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXGOMZECRAYAUODT","created_at":"2026-07-03T00:16:56.027843+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXGOMZEC","created_at":"2026-07-03T00:16:56.027843+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/ZXGOMZECRAYAUODTEPREHFT5PK","json":"https://pith.science/pith/ZXGOMZECRAYAUODTEPREHFT5PK.json","graph_json":"https://pith.science/api/pith-number/ZXGOMZECRAYAUODTEPREHFT5PK/graph.json","events_json":"https://pith.science/api/pith-number/ZXGOMZECRAYAUODTEPREHFT5PK/events.json","paper":"https://pith.science/paper/ZXGOMZEC"},"agent_actions":{"view_html":"https://pith.science/pith/ZXGOMZECRAYAUODTEPREHFT5PK","download_json":"https://pith.science/pith/ZXGOMZECRAYAUODTEPREHFT5PK.json","view_paper":"https://pith.science/paper/ZXGOMZEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01275&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXGOMZECRAYAUODTEPREHFT5PK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXGOMZECRAYAUODTEPREHFT5PK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXGOMZECRAYAUODTEPREHFT5PK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXGOMZECRAYAUODTEPREHFT5PK/action/storage_attestation","attest_author":"https://pith.science/pith/ZXGOMZECRAYAUODTEPREHFT5PK/action/author_attestation","sign_citation":"https://pith.science/pith/ZXGOMZECRAYAUODTEPREHFT5PK/action/citation_signature","submit_replication":"https://pith.science/pith/ZXGOMZECRAYAUODTEPREHFT5PK/action/replication_record"}},"created_at":"2026-07-03T00:16:56.027843+00:00","updated_at":"2026-07-03T00:16:56.027843+00:00"}