{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MPG2JXIMIWTDYLGSKI7MWVXUGG","short_pith_number":"pith:MPG2JXIM","schema_version":"1.0","canonical_sha256":"63cda4dd0c45a63c2cd2523ecb56f431b9db3540e2d2fc35a77c1535043fac43","source":{"kind":"arxiv","id":"2605.18931","version":1},"attestation_state":"computed","paper":{"title":"Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Abdelhakim Ziani (MICS), Andras Horvath (UNITO), Paolo Ballarini (MICS)","submitted_at":"2026-05-18T14:21:46Z","abstract_excerpt":"Heavy-tailed distributions are prevalent in performance evaluation, network traffic, and risk modeling. This behavior poses a fundamental challenge for modern deep generative models. Standard Variational Autoencoders (VAEs) employ Gaussian decoder likelihoods and Lipschitz-constrained neural networks, a combination that is structurally incapable of producing heavy-tailed outputs: the Gaussian tail decays exponentially, and Lipschitz continuity prevents the decoder from amplifying rare events from the latent space input to sufficiently overcome this decay. We provide both a theoretical characte"},"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":"2605.18931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T14:21:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1fa08b264fa3d858df859458a52bcf939b7473b607759d62b291e719e1700eef","abstract_canon_sha256":"6d2763f7196f42293373305d34333e03a69bcf405a0407cd3adee7954499b0d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:36.730609Z","signature_b64":"iwnij9ERPv8PGJF2idgsXpYly33+Zox10HvvXLCpv9YOkTZNikXGbwXyES54SXs2/Sb3Zj6FC9j1F4duaaflAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63cda4dd0c45a63c2cd2523ecb56f431b9db3540e2d2fc35a77c1535043fac43","last_reissued_at":"2026-05-20T00:06:36.729558Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:36.729558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Abdelhakim Ziani (MICS), Andras Horvath (UNITO), Paolo Ballarini (MICS)","submitted_at":"2026-05-18T14:21:46Z","abstract_excerpt":"Heavy-tailed distributions are prevalent in performance evaluation, network traffic, and risk modeling. This behavior poses a fundamental challenge for modern deep generative models. Standard Variational Autoencoders (VAEs) employ Gaussian decoder likelihoods and Lipschitz-constrained neural networks, a combination that is structurally incapable of producing heavy-tailed outputs: the Gaussian tail decays exponentially, and Lipschitz continuity prevents the decoder from amplifying rare events from the latent space input to sufficiently overcome this decay. We provide both a theoretical characte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18931","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/2605.18931/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":"2605.18931","created_at":"2026-05-20T00:06:36.729697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18931v1","created_at":"2026-05-20T00:06:36.729697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18931","created_at":"2026-05-20T00:06:36.729697+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPG2JXIMIWTD","created_at":"2026-05-20T00:06:36.729697+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPG2JXIMIWTDYLGS","created_at":"2026-05-20T00:06:36.729697+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPG2JXIM","created_at":"2026-05-20T00:06:36.729697+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/MPG2JXIMIWTDYLGSKI7MWVXUGG","json":"https://pith.science/pith/MPG2JXIMIWTDYLGSKI7MWVXUGG.json","graph_json":"https://pith.science/api/pith-number/MPG2JXIMIWTDYLGSKI7MWVXUGG/graph.json","events_json":"https://pith.science/api/pith-number/MPG2JXIMIWTDYLGSKI7MWVXUGG/events.json","paper":"https://pith.science/paper/MPG2JXIM"},"agent_actions":{"view_html":"https://pith.science/pith/MPG2JXIMIWTDYLGSKI7MWVXUGG","download_json":"https://pith.science/pith/MPG2JXIMIWTDYLGSKI7MWVXUGG.json","view_paper":"https://pith.science/paper/MPG2JXIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18931&json=true","fetch_graph":"https://pith.science/api/pith-number/MPG2JXIMIWTDYLGSKI7MWVXUGG/graph.json","fetch_events":"https://pith.science/api/pith-number/MPG2JXIMIWTDYLGSKI7MWVXUGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPG2JXIMIWTDYLGSKI7MWVXUGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPG2JXIMIWTDYLGSKI7MWVXUGG/action/storage_attestation","attest_author":"https://pith.science/pith/MPG2JXIMIWTDYLGSKI7MWVXUGG/action/author_attestation","sign_citation":"https://pith.science/pith/MPG2JXIMIWTDYLGSKI7MWVXUGG/action/citation_signature","submit_replication":"https://pith.science/pith/MPG2JXIMIWTDYLGSKI7MWVXUGG/action/replication_record"}},"created_at":"2026-05-20T00:06:36.729697+00:00","updated_at":"2026-05-20T00:06:36.729697+00:00"}