{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FQJUEWBMYWERKYA46MI2G3ZWP2","short_pith_number":"pith:FQJUEWBM","schema_version":"1.0","canonical_sha256":"2c1342582cc58915601cf311a36f367e8938f760af04989127668bbf33d41732","source":{"kind":"arxiv","id":"2402.03201","version":4},"attestation_state":"computed","paper":{"title":"Guidance with Spherical Gaussian Constraint for Conditional Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingya Wang, Jingyi Yu, Lingxiao Yang, Shutong Ding, Ye Shi, Yifan Cai","submitted_at":"2024-02-05T17:12:21Z","abstract_excerpt":"Recent advances in diffusion models attempt to handle conditional generative tasks by utilizing a differentiable loss function for guidance without the need for additional training. While these methods achieved certain success, they often compromise on sample quality and require small guidance step sizes, leading to longer sampling processes. This paper reveals that the fundamental issue lies in the manifold deviation during the sampling process when loss guidance is employed. We theoretically show the existence of manifold deviation by establishing a certain lower bound for the estimation err"},"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":"2402.03201","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T17:12:21Z","cross_cats_sorted":[],"title_canon_sha256":"e176e8b1f0cb6cdb9480a5fb93a3b39e99e218d6c3fc27eee71d6551fee6ba2f","abstract_canon_sha256":"4b955dfe5a0d15fd988aa7fae34b0d9b2df2cda116a170a3fe6052c728a2fadc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:13.036097Z","signature_b64":"mEjog+gxn8oWyvTBmr7kUojoviPaFIL3pJ/EHC/HDo9iPc7xOivuqkJQJ/foZMfvUmOw8oeOk7ADAn/e2GG2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c1342582cc58915601cf311a36f367e8938f760af04989127668bbf33d41732","last_reissued_at":"2026-07-05T08:40:13.035605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:13.035605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guidance with Spherical Gaussian Constraint for Conditional Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingya Wang, Jingyi Yu, Lingxiao Yang, Shutong Ding, Ye Shi, Yifan Cai","submitted_at":"2024-02-05T17:12:21Z","abstract_excerpt":"Recent advances in diffusion models attempt to handle conditional generative tasks by utilizing a differentiable loss function for guidance without the need for additional training. While these methods achieved certain success, they often compromise on sample quality and require small guidance step sizes, leading to longer sampling processes. This paper reveals that the fundamental issue lies in the manifold deviation during the sampling process when loss guidance is employed. We theoretically show the existence of manifold deviation by establishing a certain lower bound for the estimation err"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03201","kind":"arxiv","version":4},"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/2402.03201/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":"2402.03201","created_at":"2026-07-05T08:40:13.035662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03201v4","created_at":"2026-07-05T08:40:13.035662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03201","created_at":"2026-07-05T08:40:13.035662+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQJUEWBMYWER","created_at":"2026-07-05T08:40:13.035662+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQJUEWBMYWERKYA4","created_at":"2026-07-05T08:40:13.035662+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQJUEWBM","created_at":"2026-07-05T08:40:13.035662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.07715","citing_title":"Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17850","citing_title":"Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16520","citing_title":"Saving Foundation Flow-Matching Priors for Inverse Problems","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2410.00083","citing_title":"A Survey on Diffusion Models for Inverse Problems","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07150","citing_title":"FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQJUEWBMYWERKYA46MI2G3ZWP2","json":"https://pith.science/pith/FQJUEWBMYWERKYA46MI2G3ZWP2.json","graph_json":"https://pith.science/api/pith-number/FQJUEWBMYWERKYA46MI2G3ZWP2/graph.json","events_json":"https://pith.science/api/pith-number/FQJUEWBMYWERKYA46MI2G3ZWP2/events.json","paper":"https://pith.science/paper/FQJUEWBM"},"agent_actions":{"view_html":"https://pith.science/pith/FQJUEWBMYWERKYA46MI2G3ZWP2","download_json":"https://pith.science/pith/FQJUEWBMYWERKYA46MI2G3ZWP2.json","view_paper":"https://pith.science/paper/FQJUEWBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03201&json=true","fetch_graph":"https://pith.science/api/pith-number/FQJUEWBMYWERKYA46MI2G3ZWP2/graph.json","fetch_events":"https://pith.science/api/pith-number/FQJUEWBMYWERKYA46MI2G3ZWP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQJUEWBMYWERKYA46MI2G3ZWP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQJUEWBMYWERKYA46MI2G3ZWP2/action/storage_attestation","attest_author":"https://pith.science/pith/FQJUEWBMYWERKYA46MI2G3ZWP2/action/author_attestation","sign_citation":"https://pith.science/pith/FQJUEWBMYWERKYA46MI2G3ZWP2/action/citation_signature","submit_replication":"https://pith.science/pith/FQJUEWBMYWERKYA46MI2G3ZWP2/action/replication_record"}},"created_at":"2026-07-05T08:40:13.035662+00:00","updated_at":"2026-07-05T08:40:13.035662+00:00"}