{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AVH43RENQKKVLTOUNTY3ZLZSMZ","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":"25869610d6d1dd0007a927c4d438c105019e8135f02a985cd33559cd0b4bd17e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-13T09:55:51Z","title_canon_sha256":"3886e83adf6382b8de95b0dda8f2b27372762ab17ebf6676948ffa2005fc7481"},"schema_version":"1.0","source":{"id":"2605.13278","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13278","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13278v1","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13278","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"AVH43RENQKKV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"AVH43RENQKKVLTOU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"AVH43REN","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e2c1014b0322dd62326a7e3a4c692f3a6ec9a1580215097543b2e5294575ced7","target":"graph","created_at":"2026-05-18T02:44:49Z","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":3,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"PGM eliminates the early-stopping bias inherent in the score-based diffusion model and achieves non-asymptotic convergence."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization holds rigorously and directly yields a closed-form Moreau score via proximal operators that can be learned from prior samples alone."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PGM replaces the intractable likelihood score in diffusion models with a closed-form Moreau score computed via proximal operators, enabling non-asymptotic sampling for inverse problems trained only on prior data."}],"snapshot_sha256":"812e48c6a30d14e698b30942c9a5ff71c5427a112253e05ede842e249a5f690b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Score-based diffusion models demonstrate superior performance in generative tasks but encounter fundamental bottlenecks in inverse problems due to the analytical intractability of the time-dependent likelihood score. To bridge this gap, we propose a novel proximal-based generative modeling (PGM) framework that rigorously circumvents explicit likelihood evaluation. Our framework is built upon a theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization in nonsmooth optimization. This enables a new sampling mechanism driven by the proposed Moreau","authors_text":"Boyang Zhang, Ya-Feng Liu, Zhiguo Wang","cross_cats":["cs.LG"],"headline":"PGM replaces the intractable likelihood score in diffusion models with a closed-form Moreau score computed via proximal operators, enabling non-asymptotic sampling for inverse problems trained only on prior data.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-13T09:55:51Z","title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems"},"references":{"count":132,"internal_anchors":5,"resolved_work":132,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Proceedings of the 28th International Conference on Machine Learning , pages=","work_id":"f56af9f4-6863-41d7-ad3d-428f36b0db8d","year":null},{"cited_arxiv_id":"2011.13456","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"SIAM Review , volume=","work_id":"407f94c0-e357-481c-a896-7a93b1dffbcd","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Advances in Neural Information Processing Systems , volume=","work_id":"49d8a4df-67bb-49cb-9185-1d7d846f43ae","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Statistical Physics: Volume 5 , author=. 2013 , publisher=","work_id":"da20961b-d717-455a-a320-d4d40b10b949","year":2013}],"snapshot_sha256":"042b6f153dbb9b54717acde1afeb0afd7fc65644f0294852322a009eea13d7d6"},"source":{"id":"2605.13278","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T17:50:32.559283Z","id":"0b6aaa16-e9cc-421b-a4c9-298036a1975c","model_set":{"reader":"grok-4.3"},"one_line_summary":"PGM replaces the intractable likelihood score in diffusion models with a closed-form Moreau score computed via proximal operators, enabling non-asymptotic sampling for inverse problems trained only on prior data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"","strongest_claim":"PGM eliminates the early-stopping bias inherent in the score-based diffusion model and achieves non-asymptotic convergence.","weakest_assumption":"The theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization holds rigorously and directly yields a closed-form Moreau score via proximal operators that can be learned from prior samples alone."}},"verdict_id":"0b6aaa16-e9cc-421b-a4c9-298036a1975c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:277821930d3624a29c9d8da5ef80128b7cf2cb859e3b7a43c32000ffa7fe82ed","target":"record","created_at":"2026-05-18T02:44:49Z","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":"25869610d6d1dd0007a927c4d438c105019e8135f02a985cd33559cd0b4bd17e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-13T09:55:51Z","title_canon_sha256":"3886e83adf6382b8de95b0dda8f2b27372762ab17ebf6676948ffa2005fc7481"},"schema_version":"1.0","source":{"id":"2605.13278","kind":"arxiv","version":1}},"canonical_sha256":"054fcdc48d829555cdd46cf1bcaf32667ea6eb885b41b3e72f0de933db7b04f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"054fcdc48d829555cdd46cf1bcaf32667ea6eb885b41b3e72f0de933db7b04f4","first_computed_at":"2026-05-18T02:44:49.221200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:49.221200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zPw5/NWcNtS0B+nmpRJoQgS/Pn5Zue7dl8Kb6HZbrc0dZDJaFx+9SY5dHGNhnyltAY21gf3T0k0AegZ0/geiAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:49.221638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13278","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:277821930d3624a29c9d8da5ef80128b7cf2cb859e3b7a43c32000ffa7fe82ed","sha256:e2c1014b0322dd62326a7e3a4c692f3a6ec9a1580215097543b2e5294575ced7"],"state_sha256":"7467eaf8d9d45552067d015c0e87541902e43861aab9624d5edfc8341a75d314"}