{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6QMLWE2XC7ZGS3R53CFKZGIJLQ","short_pith_number":"pith:6QMLWE2X","schema_version":"1.0","canonical_sha256":"f418bb135717f2696e3dd88aac99095c3b0f5867735e3474c484189ad5920760","source":{"kind":"arxiv","id":"2505.01382","version":1},"attestation_state":"computed","paper":{"title":"Provable Efficiency of Guidance in Diffusion Models for General Data Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Gen Li, Yuchen Jiao","submitted_at":"2025-05-02T16:46:43Z","abstract_excerpt":"Diffusion models have emerged as a powerful framework for generative modeling, with guidance techniques playing a crucial role in enhancing sample quality. Despite their empirical success, a comprehensive theoretical understanding of the guidance effect remains limited. Existing studies only focus on case studies, where the distribution conditioned on each class is either isotropic Gaussian or supported on a one-dimensional interval with some extra conditions. How to analyze the guidance effect beyond these case studies remains an open question. Towards closing this gap, we make an attempt to "},"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":"2505.01382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-02T16:46:43Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"2cb81ed42190673039018e0cc781a2de14511312f0647a66d14a8b1cd249fc5d","abstract_canon_sha256":"b295176346fe8df7e2773d7bb6091b477cad7899a4645de594d5f5b401760224"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:50.038942Z","signature_b64":"hKl2nM5PNo+TSXLZe9UikneJc+gmkU5DTm68G64aElUqmmeHydcOP7vJ0sm88htmg5R1qpulhrqbUqhUS27ECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f418bb135717f2696e3dd88aac99095c3b0f5867735e3474c484189ad5920760","last_reissued_at":"2026-07-05T10:57:50.038452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:50.038452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Efficiency of Guidance in Diffusion Models for General Data Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Gen Li, Yuchen Jiao","submitted_at":"2025-05-02T16:46:43Z","abstract_excerpt":"Diffusion models have emerged as a powerful framework for generative modeling, with guidance techniques playing a crucial role in enhancing sample quality. Despite their empirical success, a comprehensive theoretical understanding of the guidance effect remains limited. Existing studies only focus on case studies, where the distribution conditioned on each class is either isotropic Gaussian or supported on a one-dimensional interval with some extra conditions. How to analyze the guidance effect beyond these case studies remains an open question. Towards closing this gap, we make an attempt to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01382","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/2505.01382/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":"2505.01382","created_at":"2026-07-05T10:57:50.038512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01382v1","created_at":"2026-07-05T10:57:50.038512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01382","created_at":"2026-07-05T10:57:50.038512+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QMLWE2XC7ZG","created_at":"2026-07-05T10:57:50.038512+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QMLWE2XC7ZGS3R5","created_at":"2026-07-05T10:57:50.038512+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QMLWE2X","created_at":"2026-07-05T10:57:50.038512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07220","citing_title":"On the Robustness of Distribution Support under Diffusion Guidance","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07220","citing_title":"On the Robustness of Distribution Support under Diffusion Guidance","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QMLWE2XC7ZGS3R53CFKZGIJLQ","json":"https://pith.science/pith/6QMLWE2XC7ZGS3R53CFKZGIJLQ.json","graph_json":"https://pith.science/api/pith-number/6QMLWE2XC7ZGS3R53CFKZGIJLQ/graph.json","events_json":"https://pith.science/api/pith-number/6QMLWE2XC7ZGS3R53CFKZGIJLQ/events.json","paper":"https://pith.science/paper/6QMLWE2X"},"agent_actions":{"view_html":"https://pith.science/pith/6QMLWE2XC7ZGS3R53CFKZGIJLQ","download_json":"https://pith.science/pith/6QMLWE2XC7ZGS3R53CFKZGIJLQ.json","view_paper":"https://pith.science/paper/6QMLWE2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01382&json=true","fetch_graph":"https://pith.science/api/pith-number/6QMLWE2XC7ZGS3R53CFKZGIJLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6QMLWE2XC7ZGS3R53CFKZGIJLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QMLWE2XC7ZGS3R53CFKZGIJLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QMLWE2XC7ZGS3R53CFKZGIJLQ/action/storage_attestation","attest_author":"https://pith.science/pith/6QMLWE2XC7ZGS3R53CFKZGIJLQ/action/author_attestation","sign_citation":"https://pith.science/pith/6QMLWE2XC7ZGS3R53CFKZGIJLQ/action/citation_signature","submit_replication":"https://pith.science/pith/6QMLWE2XC7ZGS3R53CFKZGIJLQ/action/replication_record"}},"created_at":"2026-07-05T10:57:50.038512+00:00","updated_at":"2026-07-05T10:57:50.038512+00:00"}