{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:62JE24AGAGZEDHT4OFRLRHXYYV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4bc0a6233b027cb76f303b4b0f9da2222eca9186ef0f9626749e14524b109bac","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-30T10:28:50Z","title_canon_sha256":"b67679e2c977f9358425a82ff143f5825418332a35113ff92c553de936e944e1"},"schema_version":"1.0","source":{"id":"2208.14133","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.14133","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"2208.14133v3","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14133","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"62JE24AGAGZE","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"pith_short_16","alias_value":"62JE24AGAGZEDHT4","created_at":"2026-07-05T05:59:21Z"},{"alias_kind":"pith_short_8","alias_value":"62JE24AG","created_at":"2026-07-05T05:59:21Z"}],"graph_snapshots":[{"event_id":"sha256:accb62ef8097aec5d0684e92c22400c323c87f04fd9aa5092b4e28f59f6481fb","target":"graph","created_at":"2026-07-05T05:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.14133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep generative models (DGMs) are data-eager because learning a complex model on limited data suffers from a large variance and easily overfits. Inspired by the classical perspective of the bias-variance tradeoff, we propose regularized deep generative model (Reg-DGM), which leverages a nontransferable pre-trained model to reduce the variance of generative modeling with limited data. Formally, Reg-DGM optimizes a weighted sum of a certain divergence and the expectation of an energy function, where the divergence is between the data and the model distributions, and the energy function is define","authors_text":"Chongxuan Li, Fan Bao, Hongtao Liu, Weiran Shen, XiaoDong Liu, Yong Zhong","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-30T10:28:50Z","title":"Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14133","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0d7a1e71de4795376ba9579dd178f477deb0e9715d29aa7eed845afff65af9f3","target":"record","created_at":"2026-07-05T05:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4bc0a6233b027cb76f303b4b0f9da2222eca9186ef0f9626749e14524b109bac","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-30T10:28:50Z","title_canon_sha256":"b67679e2c977f9358425a82ff143f5825418332a35113ff92c553de936e944e1"},"schema_version":"1.0","source":{"id":"2208.14133","kind":"arxiv","version":3}},"canonical_sha256":"f6924d700601b2419e7c7162b89ef8c55ea9b58b490bf9ba7834ceb3248a084a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6924d700601b2419e7c7162b89ef8c55ea9b58b490bf9ba7834ceb3248a084a","first_computed_at":"2026-07-05T05:59:21.187605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:21.187605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pX1n84/e7lhXZbP6DLXhRdt8xmR1ZSGZMgZ9QPaSt8LGJxtcThILG/5rh6ikR1UJdmegqcUnR6u0GjhVVENXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:21.188174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.14133","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d7a1e71de4795376ba9579dd178f477deb0e9715d29aa7eed845afff65af9f3","sha256:accb62ef8097aec5d0684e92c22400c323c87f04fd9aa5092b4e28f59f6481fb"],"state_sha256":"4678f5cb2329adf3c865512debdd057c6fc8e0f13e2bdb680eecbb18882275ca"}