{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YQZURXGU2FGTO3B76BPUS2MP54","short_pith_number":"pith:YQZURXGU","canonical_record":{"source":{"id":"2605.17850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T04:45:33Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NA","math.NA","math.PR"],"title_canon_sha256":"4759b1413269cca1d18579cd5b64f5f9b045b82a8aeff566be03072bf33c43c4","abstract_canon_sha256":"69002d252b172a9a9e0530b98b8b0c56cf4a3ae2fe84febe30450d1160422134"},"schema_version":"1.0"},"canonical_sha256":"c43348dcd4d14d376c3ff05f49698fef1eafc23207304957d364ec50437363e0","source":{"kind":"arxiv","id":"2605.17850","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17850","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17850v1","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17850","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"YQZURXGU2FGT","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"YQZURXGU2FGTO3B7","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"YQZURXGU","created_at":"2026-05-20T00:05:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YQZURXGU2FGTO3B76BPUS2MP54","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T04:45:33Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NA","math.NA","math.PR"],"title_canon_sha256":"4759b1413269cca1d18579cd5b64f5f9b045b82a8aeff566be03072bf33c43c4","abstract_canon_sha256":"69002d252b172a9a9e0530b98b8b0c56cf4a3ae2fe84febe30450d1160422134"},"schema_version":"1.0"},"canonical_sha256":"c43348dcd4d14d376c3ff05f49698fef1eafc23207304957d364ec50437363e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:01.639934Z","signature_b64":"nqhCLBYFpHfpvcLohRvV39/luf72GjTq6kV3BEJWyrQToUSoz/nRzal4PHJaJ4QH6EcafEXTYMZz9Va7ycQ8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c43348dcd4d14d376c3ff05f49698fef1eafc23207304957d364ec50437363e0","last_reissued_at":"2026-05-20T00:05:01.638699Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:01.638699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17850","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3p0gh85Hj6yauRR8qig0mcLtrplQG7kES5RazG2HKuX6/pzJ5aOEwRkgjZ67XdghUVAUU6nloWw02vAfgUqzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:11:44.839223Z"},"content_sha256":"a53e9e1b82cea2b2181119e14ebe70f320113a7f73d287d01bdffc0cd27b9a6f","schema_version":"1.0","event_id":"sha256:a53e9e1b82cea2b2181119e14ebe70f320113a7f73d287d01bdffc0cd27b9a6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YQZURXGU2FGTO3B76BPUS2MP54","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NA","math.NA","math.PR"],"primary_cat":"stat.ML","authors_text":"Chenyang Wang, Jose Blanchet, Weizhong Wang, Yinuo Ren, Yiping Lu","submitted_at":"2026-05-18T04:45:33Z","abstract_excerpt":"iffusion-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 wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17850","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/2605.17850/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P5mPsGJuNn+IiQ8qJU1/DNXISZZySwx+BEkFFOdww2/0dHcGEWdqCZOmQvQkZM9zOEVeBfzF7DJL+tt4M9vpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:11:44.839953Z"},"content_sha256":"3b4f3cece988ebaecb53883fda58bc867b4f8ed6e91848b8c6f59e5b6d4b22db","schema_version":"1.0","event_id":"sha256:3b4f3cece988ebaecb53883fda58bc867b4f8ed6e91848b8c6f59e5b6d4b22db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQZURXGU2FGTO3B76BPUS2MP54/bundle.json","state_url":"https://pith.science/pith/YQZURXGU2FGTO3B76BPUS2MP54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQZURXGU2FGTO3B76BPUS2MP54/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T17:11:44Z","links":{"resolver":"https://pith.science/pith/YQZURXGU2FGTO3B76BPUS2MP54","bundle":"https://pith.science/pith/YQZURXGU2FGTO3B76BPUS2MP54/bundle.json","state":"https://pith.science/pith/YQZURXGU2FGTO3B76BPUS2MP54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQZURXGU2FGTO3B76BPUS2MP54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YQZURXGU2FGTO3B76BPUS2MP54","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":"69002d252b172a9a9e0530b98b8b0c56cf4a3ae2fe84febe30450d1160422134","cross_cats_sorted":["cs.CV","cs.LG","cs.NA","math.NA","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T04:45:33Z","title_canon_sha256":"4759b1413269cca1d18579cd5b64f5f9b045b82a8aeff566be03072bf33c43c4"},"schema_version":"1.0","source":{"id":"2605.17850","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17850","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17850v1","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17850","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"YQZURXGU2FGT","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"YQZURXGU2FGTO3B7","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"YQZURXGU","created_at":"2026-05-20T00:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:3b4f3cece988ebaecb53883fda58bc867b4f8ed6e91848b8c6f59e5b6d4b22db","target":"graph","created_at":"2026-05-20T00:05:01Z","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/2605.17850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"iffusion-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 wor","authors_text":"Chenyang Wang, Jose Blanchet, Weizhong Wang, Yinuo Ren, Yiping Lu","cross_cats":["cs.CV","cs.LG","cs.NA","math.NA","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T04:45:33Z","title":"Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17850","kind":"arxiv","version":1},"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:a53e9e1b82cea2b2181119e14ebe70f320113a7f73d287d01bdffc0cd27b9a6f","target":"record","created_at":"2026-05-20T00:05:01Z","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":"69002d252b172a9a9e0530b98b8b0c56cf4a3ae2fe84febe30450d1160422134","cross_cats_sorted":["cs.CV","cs.LG","cs.NA","math.NA","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T04:45:33Z","title_canon_sha256":"4759b1413269cca1d18579cd5b64f5f9b045b82a8aeff566be03072bf33c43c4"},"schema_version":"1.0","source":{"id":"2605.17850","kind":"arxiv","version":1}},"canonical_sha256":"c43348dcd4d14d376c3ff05f49698fef1eafc23207304957d364ec50437363e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c43348dcd4d14d376c3ff05f49698fef1eafc23207304957d364ec50437363e0","first_computed_at":"2026-05-20T00:05:01.638699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:01.638699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nqhCLBYFpHfpvcLohRvV39/luf72GjTq6kV3BEJWyrQToUSoz/nRzal4PHJaJ4QH6EcafEXTYMZz9Va7ycQ8Dw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:01.639934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17850","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a53e9e1b82cea2b2181119e14ebe70f320113a7f73d287d01bdffc0cd27b9a6f","sha256:3b4f3cece988ebaecb53883fda58bc867b4f8ed6e91848b8c6f59e5b6d4b22db"],"state_sha256":"584272d0b443c2abb49dc395db9a1b9a4518c7bed8bbedee6e8905b15814b6ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IM8a/z9AGxc5FNseJR5BUvP3ylqlpSARd9jQbVuNENn0z2JtOfCft08/LgH/8jLdfK4TRNhkFYZ+ETelyzRBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:11:44.844371Z","bundle_sha256":"2f7680aec625f00a701bd84fc4ccc84c5275f3010fc4c8d7f8a3a56d2aad8743"}}