{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YGQREDCWN6SUQ6Z6ZCX6JSBYLE","short_pith_number":"pith:YGQREDCW","schema_version":"1.0","canonical_sha256":"c1a1120c566fa5487b3ec8afe4c8385900dc2522e16622add191dc00f582aec3","source":{"kind":"arxiv","id":"2605.18745","version":1},"attestation_state":"computed","paper":{"title":"SURGE: Approximation-free Training Free Particle Filter for Diffusion Surrogate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.PR","q-fin.MF","stat.CO"],"primary_cat":"stat.ML","authors_text":"Lifu Wei, Naichen Shi, Yinuo Ren, Yiping Lu","submitted_at":"2026-05-18T17:59:00Z","abstract_excerpt":"Diffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific objectives. However, most existing techniques require repeated score or gradient evaluations, introducing bias, high computational overhead, or both. We introduce \\texttt{URGE}, Unbiased Resampling via Girsanov Estimation, a derivative-free inference-time scaling algorithm that performs path-wise importance reweighting via a Girsanov change of measure. Instead of computing gradient-based particle weights in previous wo"},"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":"2605.18745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T17:59:00Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.PR","q-fin.MF","stat.CO"],"title_canon_sha256":"e0c6196ce5b05b7173691786c44fc04eeea63432cd88ffe21f0f12b4a8a8ec17","abstract_canon_sha256":"24f879ed44340383fc46f3ae7dd813f3d07bf203db82e0c7ec2c45563f46f681"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:18.766921Z","signature_b64":"PBeTYkMdLut4UXA5RT4MAIMNWMmbGxKpt0z22eDgv0watviDQf3saW/en0fFkDwBpQQ2DH00XAtpYvZLHmU/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1a1120c566fa5487b3ec8afe4c8385900dc2522e16622add191dc00f582aec3","last_reissued_at":"2026-05-20T00:06:18.766118Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:18.766118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SURGE: Approximation-free Training Free Particle Filter for Diffusion Surrogate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.PR","q-fin.MF","stat.CO"],"primary_cat":"stat.ML","authors_text":"Lifu Wei, Naichen Shi, Yinuo Ren, Yiping Lu","submitted_at":"2026-05-18T17:59:00Z","abstract_excerpt":"Diffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific objectives. However, most existing techniques require repeated score or gradient evaluations, introducing bias, high computational overhead, or both. We introduce \\texttt{URGE}, Unbiased Resampling via Girsanov Estimation, a derivative-free inference-time scaling algorithm that performs path-wise importance reweighting via a Girsanov change of measure. Instead of computing gradient-based particle weights in previous wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18745","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/2605.18745/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:58.989097Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"43510b5aa2c38009c20b7b2eac516994143c4a95db5dda326a438d0fa3c9bc05"},"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":"2605.18745","created_at":"2026-05-20T00:06:18.766248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18745v1","created_at":"2026-05-20T00:06:18.766248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18745","created_at":"2026-05-20T00:06:18.766248+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGQREDCWN6SU","created_at":"2026-05-20T00:06:18.766248+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGQREDCWN6SUQ6Z6","created_at":"2026-05-20T00:06:18.766248+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGQREDCW","created_at":"2026-05-20T00:06:18.766248+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/YGQREDCWN6SUQ6Z6ZCX6JSBYLE","json":"https://pith.science/pith/YGQREDCWN6SUQ6Z6ZCX6JSBYLE.json","graph_json":"https://pith.science/api/pith-number/YGQREDCWN6SUQ6Z6ZCX6JSBYLE/graph.json","events_json":"https://pith.science/api/pith-number/YGQREDCWN6SUQ6Z6ZCX6JSBYLE/events.json","paper":"https://pith.science/paper/YGQREDCW"},"agent_actions":{"view_html":"https://pith.science/pith/YGQREDCWN6SUQ6Z6ZCX6JSBYLE","download_json":"https://pith.science/pith/YGQREDCWN6SUQ6Z6ZCX6JSBYLE.json","view_paper":"https://pith.science/paper/YGQREDCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18745&json=true","fetch_graph":"https://pith.science/api/pith-number/YGQREDCWN6SUQ6Z6ZCX6JSBYLE/graph.json","fetch_events":"https://pith.science/api/pith-number/YGQREDCWN6SUQ6Z6ZCX6JSBYLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGQREDCWN6SUQ6Z6ZCX6JSBYLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGQREDCWN6SUQ6Z6ZCX6JSBYLE/action/storage_attestation","attest_author":"https://pith.science/pith/YGQREDCWN6SUQ6Z6ZCX6JSBYLE/action/author_attestation","sign_citation":"https://pith.science/pith/YGQREDCWN6SUQ6Z6ZCX6JSBYLE/action/citation_signature","submit_replication":"https://pith.science/pith/YGQREDCWN6SUQ6Z6ZCX6JSBYLE/action/replication_record"}},"created_at":"2026-05-20T00:06:18.766248+00:00","updated_at":"2026-05-20T00:06:18.766248+00:00"}