{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OL5Q2FDIJ3VZKDLCKJ22OPDENP","short_pith_number":"pith:OL5Q2FDI","schema_version":"1.0","canonical_sha256":"72fb0d14684eeb950d625275a73c646be00d276508be25bb0a85cb09669a8c66","source":{"kind":"arxiv","id":"2601.08379","version":2},"attestation_state":"computed","paper":{"title":"MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Farzan Farnia, Matina Mahdizadeh Sani, Mohammad Jalali, Nima Jamali","submitted_at":"2026-01-13T09:42:57Z","abstract_excerpt":"Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data. Such mismatches are especially problematic in domain adaptation tasks, where only a few reference examples are available and retraining the diffusion model is infeasible. Existing inference-time guidance methods can adjust sampling trajectories, but they typically optimize surrogate objectives such as classifier likelihoods rather than directly aligning with the target distributio"},"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":"2601.08379","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-13T09:42:57Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"58fcaedeaa9a96ed87d1460ea830e72e8e290e6a77649bb890e2fb998bbf0294","abstract_canon_sha256":"58f19c914edab393acd3e0deb72cea7c0b70d16e31cb1819be9ef8aa5ddc5358"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:52.469299Z","signature_b64":"IvDnb9lUJa1Zoo0pCxsg+VlVCqAgors9uuD5S6f4CcgepofJ4RupQknwpbuaK2+Ijj+oUaUKduNUNGw5bBZmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72fb0d14684eeb950d625275a73c646be00d276508be25bb0a85cb09669a8c66","last_reissued_at":"2026-06-10T01:09:52.468500Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:52.468500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Farzan Farnia, Matina Mahdizadeh Sani, Mohammad Jalali, Nima Jamali","submitted_at":"2026-01-13T09:42:57Z","abstract_excerpt":"Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data. Such mismatches are especially problematic in domain adaptation tasks, where only a few reference examples are available and retraining the diffusion model is infeasible. Existing inference-time guidance methods can adjust sampling trajectories, but they typically optimize surrogate objectives such as classifier likelihoods rather than directly aligning with the target distributio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.08379","kind":"arxiv","version":2},"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/2601.08379/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":"2601.08379","created_at":"2026-06-10T01:09:52.468606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.08379v2","created_at":"2026-06-10T01:09:52.468606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.08379","created_at":"2026-06-10T01:09:52.468606+00:00"},{"alias_kind":"pith_short_12","alias_value":"OL5Q2FDIJ3VZ","created_at":"2026-06-10T01:09:52.468606+00:00"},{"alias_kind":"pith_short_16","alias_value":"OL5Q2FDIJ3VZKDLC","created_at":"2026-06-10T01:09:52.468606+00:00"},{"alias_kind":"pith_short_8","alias_value":"OL5Q2FDI","created_at":"2026-06-10T01:09:52.468606+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/OL5Q2FDIJ3VZKDLCKJ22OPDENP","json":"https://pith.science/pith/OL5Q2FDIJ3VZKDLCKJ22OPDENP.json","graph_json":"https://pith.science/api/pith-number/OL5Q2FDIJ3VZKDLCKJ22OPDENP/graph.json","events_json":"https://pith.science/api/pith-number/OL5Q2FDIJ3VZKDLCKJ22OPDENP/events.json","paper":"https://pith.science/paper/OL5Q2FDI"},"agent_actions":{"view_html":"https://pith.science/pith/OL5Q2FDIJ3VZKDLCKJ22OPDENP","download_json":"https://pith.science/pith/OL5Q2FDIJ3VZKDLCKJ22OPDENP.json","view_paper":"https://pith.science/paper/OL5Q2FDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.08379&json=true","fetch_graph":"https://pith.science/api/pith-number/OL5Q2FDIJ3VZKDLCKJ22OPDENP/graph.json","fetch_events":"https://pith.science/api/pith-number/OL5Q2FDIJ3VZKDLCKJ22OPDENP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OL5Q2FDIJ3VZKDLCKJ22OPDENP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OL5Q2FDIJ3VZKDLCKJ22OPDENP/action/storage_attestation","attest_author":"https://pith.science/pith/OL5Q2FDIJ3VZKDLCKJ22OPDENP/action/author_attestation","sign_citation":"https://pith.science/pith/OL5Q2FDIJ3VZKDLCKJ22OPDENP/action/citation_signature","submit_replication":"https://pith.science/pith/OL5Q2FDIJ3VZKDLCKJ22OPDENP/action/replication_record"}},"created_at":"2026-06-10T01:09:52.468606+00:00","updated_at":"2026-06-10T01:09:52.468606+00:00"}