{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VD5J4XIKU3USY3XRVPUI4SY4YW","short_pith_number":"pith:VD5J4XIK","schema_version":"1.0","canonical_sha256":"a8fa9e5d0aa6e92c6ef1abe88e4b1cc5aabf33c3995e7d6f2be6a1a69b0cfdb7","source":{"kind":"arxiv","id":"2505.24222","version":1},"attestation_state":"computed","paper":{"title":"Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Chen Li, Fangyikang Wang, Hanbin Zhao, Hubery Yin, Hui Qian, Huminhao Zhu, Lei Qian, Shaobin Zhuang, Yanlong Tang, Yilin Zhang, Yinan Li","submitted_at":"2025-05-30T05:21:44Z","abstract_excerpt":"The diffusion models (DMs) have demonstrated the remarkable capability of generating images via learning the noised score function of data distribution. Current DM sampling techniques typically rely on first-order Langevin dynamics at each noise level, with efforts concentrated on refining inter-level denoising strategies. While leveraging additional second-order Hessian geometry to enhance the sampling quality of Langevin is a common practice in Markov chain Monte Carlo (MCMC), the naive attempts to utilize Hessian geometry in high-dimensional DMs lead to quadratic-complexity computational co"},"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":"2505.24222","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T05:21:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c5266532fbe8c7311c4d825bd27df2ad81915fdd7f6aa4fc6a402154d747c88d","abstract_canon_sha256":"a4ffc7881ee04eb8a10d2606d4ff4877f0593a3092391c5711251b17fba3c9ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:44.462803Z","signature_b64":"7w5598x4nBKBSI0w9lmrUome8GwehaDnahv4bTwbCSqnSu8JZDlfFN2HByKgjhyD9EH0exE/9/Al8xDQzq9nBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8fa9e5d0aa6e92c6ef1abe88e4b1cc5aabf33c3995e7d6f2be6a1a69b0cfdb7","last_reissued_at":"2026-07-05T11:12:44.462291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:44.462291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Chen Li, Fangyikang Wang, Hanbin Zhao, Hubery Yin, Hui Qian, Huminhao Zhu, Lei Qian, Shaobin Zhuang, Yanlong Tang, Yilin Zhang, Yinan Li","submitted_at":"2025-05-30T05:21:44Z","abstract_excerpt":"The diffusion models (DMs) have demonstrated the remarkable capability of generating images via learning the noised score function of data distribution. Current DM sampling techniques typically rely on first-order Langevin dynamics at each noise level, with efforts concentrated on refining inter-level denoising strategies. While leveraging additional second-order Hessian geometry to enhance the sampling quality of Langevin is a common practice in Markov chain Monte Carlo (MCMC), the naive attempts to utilize Hessian geometry in high-dimensional DMs lead to quadratic-complexity computational co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24222","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/2505.24222/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":"2505.24222","created_at":"2026-07-05T11:12:44.462362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24222v1","created_at":"2026-07-05T11:12:44.462362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24222","created_at":"2026-07-05T11:12:44.462362+00:00"},{"alias_kind":"pith_short_12","alias_value":"VD5J4XIKU3US","created_at":"2026-07-05T11:12:44.462362+00:00"},{"alias_kind":"pith_short_16","alias_value":"VD5J4XIKU3USY3XR","created_at":"2026-07-05T11:12:44.462362+00:00"},{"alias_kind":"pith_short_8","alias_value":"VD5J4XIK","created_at":"2026-07-05T11:12:44.462362+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/VD5J4XIKU3USY3XRVPUI4SY4YW","json":"https://pith.science/pith/VD5J4XIKU3USY3XRVPUI4SY4YW.json","graph_json":"https://pith.science/api/pith-number/VD5J4XIKU3USY3XRVPUI4SY4YW/graph.json","events_json":"https://pith.science/api/pith-number/VD5J4XIKU3USY3XRVPUI4SY4YW/events.json","paper":"https://pith.science/paper/VD5J4XIK"},"agent_actions":{"view_html":"https://pith.science/pith/VD5J4XIKU3USY3XRVPUI4SY4YW","download_json":"https://pith.science/pith/VD5J4XIKU3USY3XRVPUI4SY4YW.json","view_paper":"https://pith.science/paper/VD5J4XIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24222&json=true","fetch_graph":"https://pith.science/api/pith-number/VD5J4XIKU3USY3XRVPUI4SY4YW/graph.json","fetch_events":"https://pith.science/api/pith-number/VD5J4XIKU3USY3XRVPUI4SY4YW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VD5J4XIKU3USY3XRVPUI4SY4YW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VD5J4XIKU3USY3XRVPUI4SY4YW/action/storage_attestation","attest_author":"https://pith.science/pith/VD5J4XIKU3USY3XRVPUI4SY4YW/action/author_attestation","sign_citation":"https://pith.science/pith/VD5J4XIKU3USY3XRVPUI4SY4YW/action/citation_signature","submit_replication":"https://pith.science/pith/VD5J4XIKU3USY3XRVPUI4SY4YW/action/replication_record"}},"created_at":"2026-07-05T11:12:44.462362+00:00","updated_at":"2026-07-05T11:12:44.462362+00:00"}