{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X6EXI3HC25NOQDOMSHRSIHOSBU","short_pith_number":"pith:X6EXI3HC","schema_version":"1.0","canonical_sha256":"bf89746ce2d75ae80dcc91e3241dd20d33acdf8836b72f5cbc54b8c2545c1837","source":{"kind":"arxiv","id":"2403.01639","version":1},"attestation_state":"computed","paper":{"title":"Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mengdi Wang, Minshuo Chen, Yuchen Wu, Yuting Wei, Zihao Li","submitted_at":"2024-03-03T23:15:48Z","abstract_excerpt":"Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. Such information is coined as guidance. For example, in text-to-image synthesis, text input is encoded as guidance to generate semantically aligned images. Proper guidance inputs are closely tied to the performance of diffusion models. A common observation is that strong guidance promotes a tight alignment to the task-specific information, while reducing the diversity of the generated samples. In this paper, we provide the first theoretical "},"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":"2403.01639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-03T23:15:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"650fa5acc53ee000f94d669c37cbf86b59403731ee48fa796964a73f441b68af","abstract_canon_sha256":"cc5d8fe744cdaaa811eaa50b87ce2ed4976dc3bd5226367d2fc6b157a9ed3b7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:50.115062Z","signature_b64":"sDbGk1g09cNjbTM9KqnHNyLQiNT0eovsuF/g1wJjN4dxNxr+j85zGjZhsOEpxks69rjVxGdC3I9HHWF4Yr9VAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf89746ce2d75ae80dcc91e3241dd20d33acdf8836b72f5cbc54b8c2545c1837","last_reissued_at":"2026-07-05T07:51:50.114696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:50.114696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mengdi Wang, Minshuo Chen, Yuchen Wu, Yuting Wei, Zihao Li","submitted_at":"2024-03-03T23:15:48Z","abstract_excerpt":"Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. Such information is coined as guidance. For example, in text-to-image synthesis, text input is encoded as guidance to generate semantically aligned images. Proper guidance inputs are closely tied to the performance of diffusion models. A common observation is that strong guidance promotes a tight alignment to the task-specific information, while reducing the diversity of the generated samples. In this paper, we provide the first theoretical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01639","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/2403.01639/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":"2403.01639","created_at":"2026-07-05T07:51:50.114762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01639v1","created_at":"2026-07-05T07:51:50.114762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01639","created_at":"2026-07-05T07:51:50.114762+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6EXI3HC25NO","created_at":"2026-07-05T07:51:50.114762+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6EXI3HC25NOQDOM","created_at":"2026-07-05T07:51:50.114762+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6EXI3HC","created_at":"2026-07-05T07:51:50.114762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10944","citing_title":"Non-asymptotic convergence bound of conditional diffusion models","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6EXI3HC25NOQDOMSHRSIHOSBU","json":"https://pith.science/pith/X6EXI3HC25NOQDOMSHRSIHOSBU.json","graph_json":"https://pith.science/api/pith-number/X6EXI3HC25NOQDOMSHRSIHOSBU/graph.json","events_json":"https://pith.science/api/pith-number/X6EXI3HC25NOQDOMSHRSIHOSBU/events.json","paper":"https://pith.science/paper/X6EXI3HC"},"agent_actions":{"view_html":"https://pith.science/pith/X6EXI3HC25NOQDOMSHRSIHOSBU","download_json":"https://pith.science/pith/X6EXI3HC25NOQDOMSHRSIHOSBU.json","view_paper":"https://pith.science/paper/X6EXI3HC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01639&json=true","fetch_graph":"https://pith.science/api/pith-number/X6EXI3HC25NOQDOMSHRSIHOSBU/graph.json","fetch_events":"https://pith.science/api/pith-number/X6EXI3HC25NOQDOMSHRSIHOSBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6EXI3HC25NOQDOMSHRSIHOSBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6EXI3HC25NOQDOMSHRSIHOSBU/action/storage_attestation","attest_author":"https://pith.science/pith/X6EXI3HC25NOQDOMSHRSIHOSBU/action/author_attestation","sign_citation":"https://pith.science/pith/X6EXI3HC25NOQDOMSHRSIHOSBU/action/citation_signature","submit_replication":"https://pith.science/pith/X6EXI3HC25NOQDOMSHRSIHOSBU/action/replication_record"}},"created_at":"2026-07-05T07:51:50.114762+00:00","updated_at":"2026-07-05T07:51:50.114762+00:00"}