{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C26QXQ2OLDOKO3CFMY37AO332D","short_pith_number":"pith:C26QXQ2O","schema_version":"1.0","canonical_sha256":"16bd0bc34e58dca76c456637f03b7bd0e6982ee2ab8c9c94a5f79cc254296280","source":{"kind":"arxiv","id":"2512.07778","version":2},"attestation_state":"computed","paper":{"title":"Distribution Matching Variational AutoEncoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Han Hu, Jianning Pei, Liwei Wang, Mengde Xu, Sen Ye, Shuyang Gu","submitted_at":"2025-12-08T17:59:47Z","abstract_excerpt":"Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space without explicitly shaping its distribution, making it unclear which types of distributions are optimal for modeling. We introduce \\textbf{Distribution-Matching VAE} (\\textbf{DMVAE}), which explicitly aligns the encoder's latent distribution with an arbitrary reference distribution via a distribution matching constraint. This generalizes beyond the Gaussian prior"},"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":"2512.07778","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-08T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"0db76240030ad503a5416b7322e31f75631942edf1d01a69132f4f2c950defca","abstract_canon_sha256":"fc08cfa6f62be199aee2a4c0938ad51a98000988c5c168114d6d45a442879950"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:30.459179Z","signature_b64":"2Czm1wPgiYn5M2m0skDfzLCw/yXNgaap9JLaBO1NxMtKFUUrbZ1qwVK25+n11PY1mx7K62Zyfm0bEVVS9SqHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16bd0bc34e58dca76c456637f03b7bd0e6982ee2ab8c9c94a5f79cc254296280","last_reissued_at":"2026-06-30T01:17:30.458471Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:30.458471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution Matching Variational AutoEncoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Han Hu, Jianning Pei, Liwei Wang, Mengde Xu, Sen Ye, Shuyang Gu","submitted_at":"2025-12-08T17:59:47Z","abstract_excerpt":"Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space without explicitly shaping its distribution, making it unclear which types of distributions are optimal for modeling. We introduce \\textbf{Distribution-Matching VAE} (\\textbf{DMVAE}), which explicitly aligns the encoder's latent distribution with an arbitrary reference distribution via a distribution matching constraint. This generalizes beyond the Gaussian prior"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.07778","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.07778/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":"2512.07778","created_at":"2026-06-30T01:17:30.458555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.07778v2","created_at":"2026-06-30T01:17:30.458555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.07778","created_at":"2026-06-30T01:17:30.458555+00:00"},{"alias_kind":"pith_short_12","alias_value":"C26QXQ2OLDOK","created_at":"2026-06-30T01:17:30.458555+00:00"},{"alias_kind":"pith_short_16","alias_value":"C26QXQ2OLDOKO3CF","created_at":"2026-06-30T01:17:30.458555+00:00"},{"alias_kind":"pith_short_8","alias_value":"C26QXQ2O","created_at":"2026-06-30T01:17:30.458555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.03578","citing_title":"Diffusing in the Right Space: A Systematic Study of Latent Diffusability","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22777","citing_title":"DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C26QXQ2OLDOKO3CFMY37AO332D","json":"https://pith.science/pith/C26QXQ2OLDOKO3CFMY37AO332D.json","graph_json":"https://pith.science/api/pith-number/C26QXQ2OLDOKO3CFMY37AO332D/graph.json","events_json":"https://pith.science/api/pith-number/C26QXQ2OLDOKO3CFMY37AO332D/events.json","paper":"https://pith.science/paper/C26QXQ2O"},"agent_actions":{"view_html":"https://pith.science/pith/C26QXQ2OLDOKO3CFMY37AO332D","download_json":"https://pith.science/pith/C26QXQ2OLDOKO3CFMY37AO332D.json","view_paper":"https://pith.science/paper/C26QXQ2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.07778&json=true","fetch_graph":"https://pith.science/api/pith-number/C26QXQ2OLDOKO3CFMY37AO332D/graph.json","fetch_events":"https://pith.science/api/pith-number/C26QXQ2OLDOKO3CFMY37AO332D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C26QXQ2OLDOKO3CFMY37AO332D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C26QXQ2OLDOKO3CFMY37AO332D/action/storage_attestation","attest_author":"https://pith.science/pith/C26QXQ2OLDOKO3CFMY37AO332D/action/author_attestation","sign_citation":"https://pith.science/pith/C26QXQ2OLDOKO3CFMY37AO332D/action/citation_signature","submit_replication":"https://pith.science/pith/C26QXQ2OLDOKO3CFMY37AO332D/action/replication_record"}},"created_at":"2026-06-30T01:17:30.458555+00:00","updated_at":"2026-06-30T01:17:30.458555+00:00"}