{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NJEK4LAVUKKETVZUFLKPUZ7S3Q","short_pith_number":"pith:NJEK4LAV","schema_version":"1.0","canonical_sha256":"6a48ae2c15a29449d7342ad4fa67f2dc270b95a6a51b301f554d3c4b5c0e5a4a","source":{"kind":"arxiv","id":"2507.05482","version":3},"attestation_state":"computed","paper":{"title":"Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandros Kalousis, Lionel Blond\\'e, Van Khoa Nguyen","submitted_at":"2025-07-07T21:14:27Z","abstract_excerpt":"Training-free diffusion guidance offers a flexible framework for leveraging off-the-shelf classifiers without additional training. Yet, current approaches hinge on posterior approximations via Tweedie's formula, which often yield unreliable guidance, particularly in low-density regions. Stochastic optimal control (SOC), in contrast, enables principled posterior sampling but remains computationally prohibitive for efficient inference. In this work, we reconcile the strengths of these paradigms by introducing Stein Diffusion Guidance (SDG), a novel training-free framework grounded in a surrogate"},"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":"2507.05482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T21:14:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"288984073aea646fb6c8ba413be7cd058b44794a296244d853f5d2fdc3d275e0","abstract_canon_sha256":"63d7c22f00208ef7bdb7add5b585b065e6df8fe74b7257b38a9c1f44ff0d8c4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:30.521742Z","signature_b64":"Dj3fOZ8Vguqbne9YtCFk70O6HW7sLr3ziut58qg77LPnGMNHumL0R9DpK+B0uneddZ6GGOHrRmyNRvwDNWb8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a48ae2c15a29449d7342ad4fa67f2dc270b95a6a51b301f554d3c4b5c0e5a4a","last_reissued_at":"2026-05-20T00:05:30.520929Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:30.520929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandros Kalousis, Lionel Blond\\'e, Van Khoa Nguyen","submitted_at":"2025-07-07T21:14:27Z","abstract_excerpt":"Training-free diffusion guidance offers a flexible framework for leveraging off-the-shelf classifiers without additional training. Yet, current approaches hinge on posterior approximations via Tweedie's formula, which often yield unreliable guidance, particularly in low-density regions. Stochastic optimal control (SOC), in contrast, enables principled posterior sampling but remains computationally prohibitive for efficient inference. In this work, we reconcile the strengths of these paradigms by introducing Stein Diffusion Guidance (SDG), a novel training-free framework grounded in a surrogate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05482","kind":"arxiv","version":3},"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/2507.05482/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":"2507.05482","created_at":"2026-05-20T00:05:30.521062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05482v3","created_at":"2026-05-20T00:05:30.521062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05482","created_at":"2026-05-20T00:05:30.521062+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJEK4LAVUKKE","created_at":"2026-05-20T00:05:30.521062+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJEK4LAVUKKETVZU","created_at":"2026-05-20T00:05:30.521062+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJEK4LAV","created_at":"2026-05-20T00:05:30.521062+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/NJEK4LAVUKKETVZUFLKPUZ7S3Q","json":"https://pith.science/pith/NJEK4LAVUKKETVZUFLKPUZ7S3Q.json","graph_json":"https://pith.science/api/pith-number/NJEK4LAVUKKETVZUFLKPUZ7S3Q/graph.json","events_json":"https://pith.science/api/pith-number/NJEK4LAVUKKETVZUFLKPUZ7S3Q/events.json","paper":"https://pith.science/paper/NJEK4LAV"},"agent_actions":{"view_html":"https://pith.science/pith/NJEK4LAVUKKETVZUFLKPUZ7S3Q","download_json":"https://pith.science/pith/NJEK4LAVUKKETVZUFLKPUZ7S3Q.json","view_paper":"https://pith.science/paper/NJEK4LAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05482&json=true","fetch_graph":"https://pith.science/api/pith-number/NJEK4LAVUKKETVZUFLKPUZ7S3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/NJEK4LAVUKKETVZUFLKPUZ7S3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJEK4LAVUKKETVZUFLKPUZ7S3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJEK4LAVUKKETVZUFLKPUZ7S3Q/action/storage_attestation","attest_author":"https://pith.science/pith/NJEK4LAVUKKETVZUFLKPUZ7S3Q/action/author_attestation","sign_citation":"https://pith.science/pith/NJEK4LAVUKKETVZUFLKPUZ7S3Q/action/citation_signature","submit_replication":"https://pith.science/pith/NJEK4LAVUKKETVZUFLKPUZ7S3Q/action/replication_record"}},"created_at":"2026-05-20T00:05:30.521062+00:00","updated_at":"2026-05-20T00:05:30.521062+00:00"}