{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ITZTCTKUTELIQJOKASTUQYPAO4","short_pith_number":"pith:ITZTCTKU","schema_version":"1.0","canonical_sha256":"44f3314d5499168825ca04a74861e0773bdbd6917d573678dac81342d52d17ac","source":{"kind":"arxiv","id":"2312.14965","version":1},"attestation_state":"computed","paper":{"title":"Unraveling the Temporal Dynamics of the Unet in Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anna Vilanova, Chen Zhu-Tian, Hanspeter Pfister, Hendrik Strobelt, Nicola Pezzotti, Vidya Prasad","submitted_at":"2023-12-17T04:40:33Z","abstract_excerpt":"Diffusion models have garnered significant attention since they can effectively learn complex multivariate Gaussian distributions, resulting in diverse, high-quality outcomes. They introduce Gaussian noise into training data and reconstruct the original data iteratively. Central to this iterative process is a single Unet, adapting across time steps to facilitate generation. Recent work revealed the presence of composition and denoising phases in this generation process, raising questions about the Unets' varying roles. Our study dives into the dynamic behavior of Unets within denoising diffusi"},"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":"2312.14965","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T04:40:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"65725f91f55e5ceb1d13aed0d3e24df6d123ca9ebf88595b655d0c921cc72ed7","abstract_canon_sha256":"b7ab47773a33425a2d4536fb041ddca9f59f93e7c81fe879cdcb57a6e0028832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:28.885734Z","signature_b64":"28uOv1f8Q5qpimxky66WPE9B5kK78+mIL162MlOxTjZ33XeIl/AkFrid9e6auKBQHMbmXlThmAb5d2/I++8oBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44f3314d5499168825ca04a74861e0773bdbd6917d573678dac81342d52d17ac","last_reissued_at":"2026-07-05T07:27:28.885328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:28.885328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unraveling the Temporal Dynamics of the Unet in Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anna Vilanova, Chen Zhu-Tian, Hanspeter Pfister, Hendrik Strobelt, Nicola Pezzotti, Vidya Prasad","submitted_at":"2023-12-17T04:40:33Z","abstract_excerpt":"Diffusion models have garnered significant attention since they can effectively learn complex multivariate Gaussian distributions, resulting in diverse, high-quality outcomes. They introduce Gaussian noise into training data and reconstruct the original data iteratively. Central to this iterative process is a single Unet, adapting across time steps to facilitate generation. Recent work revealed the presence of composition and denoising phases in this generation process, raising questions about the Unets' varying roles. Our study dives into the dynamic behavior of Unets within denoising diffusi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14965","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/2312.14965/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":"2312.14965","created_at":"2026-07-05T07:27:28.885387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14965v1","created_at":"2026-07-05T07:27:28.885387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14965","created_at":"2026-07-05T07:27:28.885387+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITZTCTKUTELI","created_at":"2026-07-05T07:27:28.885387+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITZTCTKUTELIQJOK","created_at":"2026-07-05T07:27:28.885387+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITZTCTKU","created_at":"2026-07-05T07:27:28.885387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02104","citing_title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","ref_index":285,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ITZTCTKUTELIQJOKASTUQYPAO4","json":"https://pith.science/pith/ITZTCTKUTELIQJOKASTUQYPAO4.json","graph_json":"https://pith.science/api/pith-number/ITZTCTKUTELIQJOKASTUQYPAO4/graph.json","events_json":"https://pith.science/api/pith-number/ITZTCTKUTELIQJOKASTUQYPAO4/events.json","paper":"https://pith.science/paper/ITZTCTKU"},"agent_actions":{"view_html":"https://pith.science/pith/ITZTCTKUTELIQJOKASTUQYPAO4","download_json":"https://pith.science/pith/ITZTCTKUTELIQJOKASTUQYPAO4.json","view_paper":"https://pith.science/paper/ITZTCTKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14965&json=true","fetch_graph":"https://pith.science/api/pith-number/ITZTCTKUTELIQJOKASTUQYPAO4/graph.json","fetch_events":"https://pith.science/api/pith-number/ITZTCTKUTELIQJOKASTUQYPAO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITZTCTKUTELIQJOKASTUQYPAO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITZTCTKUTELIQJOKASTUQYPAO4/action/storage_attestation","attest_author":"https://pith.science/pith/ITZTCTKUTELIQJOKASTUQYPAO4/action/author_attestation","sign_citation":"https://pith.science/pith/ITZTCTKUTELIQJOKASTUQYPAO4/action/citation_signature","submit_replication":"https://pith.science/pith/ITZTCTKUTELIQJOKASTUQYPAO4/action/replication_record"}},"created_at":"2026-07-05T07:27:28.885387+00:00","updated_at":"2026-07-05T07:27:28.885387+00:00"}