{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W3E4PL7J6DTSX6MH37FIH5QQCO","short_pith_number":"pith:W3E4PL7J","schema_version":"1.0","canonical_sha256":"b6c9c7afe9f0e72bf987dfca83f6101388204619e8163e7a842271aaabeb8b2e","source":{"kind":"arxiv","id":"2312.04410","version":1},"attestation_state":"computed","paper":{"title":"Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofei Wang, Gao Huang, Humphrey Shi, Jiayi Guo, Manushree Vasu, Shiji Song, Xingqian Xu, Yifan Pu, Zanlin Ni","submitted_at":"2023-12-07T16:26:23Z","abstract_excerpt":"Recently, diffusion models have made remarkable progress in text-to-image (T2I) generation, synthesizing images with high fidelity and diverse contents. Despite this advancement, latent space smoothness within diffusion models remains largely unexplored. Smooth latent spaces ensure that a perturbation on an input latent corresponds to a steady change in the output image. This property proves beneficial in downstream tasks, including image interpolation, inversion, and editing. In this work, we expose the non-smoothness of diffusion latent spaces by observing noticeable visual fluctuations resu"},"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":"2312.04410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T16:26:23Z","cross_cats_sorted":[],"title_canon_sha256":"1b465df6e1c943f0150f896b86a1d5ecbc07e81b61ffcda956b42ea09ac20924","abstract_canon_sha256":"98dcc3168347e7a2eaedf8b8b7f6ece067ed10920563e137f8b8bcd854316d33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:34.096816Z","signature_b64":"xRRCEJ7dieL27MFB8jK5Q9R+vcbsKEh4p9y8A2Zfrm/0Xe45D3iQs4UKB60qZRGRUPrhfGWGvMo4OqcvabiUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6c9c7afe9f0e72bf987dfca83f6101388204619e8163e7a842271aaabeb8b2e","last_reissued_at":"2026-07-05T07:21:34.096236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:34.096236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofei Wang, Gao Huang, Humphrey Shi, Jiayi Guo, Manushree Vasu, Shiji Song, Xingqian Xu, Yifan Pu, Zanlin Ni","submitted_at":"2023-12-07T16:26:23Z","abstract_excerpt":"Recently, diffusion models have made remarkable progress in text-to-image (T2I) generation, synthesizing images with high fidelity and diverse contents. Despite this advancement, latent space smoothness within diffusion models remains largely unexplored. Smooth latent spaces ensure that a perturbation on an input latent corresponds to a steady change in the output image. This property proves beneficial in downstream tasks, including image interpolation, inversion, and editing. In this work, we expose the non-smoothness of diffusion latent spaces by observing noticeable visual fluctuations resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04410","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/2312.04410/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":"2312.04410","created_at":"2026-07-05T07:21:34.096289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04410v1","created_at":"2026-07-05T07:21:34.096289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04410","created_at":"2026-07-05T07:21:34.096289+00:00"},{"alias_kind":"pith_short_12","alias_value":"W3E4PL7J6DTS","created_at":"2026-07-05T07:21:34.096289+00:00"},{"alias_kind":"pith_short_16","alias_value":"W3E4PL7J6DTSX6MH","created_at":"2026-07-05T07:21:34.096289+00:00"},{"alias_kind":"pith_short_8","alias_value":"W3E4PL7J","created_at":"2026-07-05T07:21:34.096289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15571","citing_title":"Cross-Cultural Fashion Design via Interactive Large Language Models and Diffusion Models","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W3E4PL7J6DTSX6MH37FIH5QQCO","json":"https://pith.science/pith/W3E4PL7J6DTSX6MH37FIH5QQCO.json","graph_json":"https://pith.science/api/pith-number/W3E4PL7J6DTSX6MH37FIH5QQCO/graph.json","events_json":"https://pith.science/api/pith-number/W3E4PL7J6DTSX6MH37FIH5QQCO/events.json","paper":"https://pith.science/paper/W3E4PL7J"},"agent_actions":{"view_html":"https://pith.science/pith/W3E4PL7J6DTSX6MH37FIH5QQCO","download_json":"https://pith.science/pith/W3E4PL7J6DTSX6MH37FIH5QQCO.json","view_paper":"https://pith.science/paper/W3E4PL7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04410&json=true","fetch_graph":"https://pith.science/api/pith-number/W3E4PL7J6DTSX6MH37FIH5QQCO/graph.json","fetch_events":"https://pith.science/api/pith-number/W3E4PL7J6DTSX6MH37FIH5QQCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W3E4PL7J6DTSX6MH37FIH5QQCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W3E4PL7J6DTSX6MH37FIH5QQCO/action/storage_attestation","attest_author":"https://pith.science/pith/W3E4PL7J6DTSX6MH37FIH5QQCO/action/author_attestation","sign_citation":"https://pith.science/pith/W3E4PL7J6DTSX6MH37FIH5QQCO/action/citation_signature","submit_replication":"https://pith.science/pith/W3E4PL7J6DTSX6MH37FIH5QQCO/action/replication_record"}},"created_at":"2026-07-05T07:21:34.096289+00:00","updated_at":"2026-07-05T07:21:34.096289+00:00"}