{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DMPWA53M2VTAXNMPX6CSIVJYJL","short_pith_number":"pith:DMPWA53M","schema_version":"1.0","canonical_sha256":"1b1f60776cd5660bb58fbf852455384adc1d73384aeed5a35ecf8d0337cd972d","source":{"kind":"arxiv","id":"2405.17082","version":2},"attestation_state":"computed","paper":{"title":"Ensembling Diffusion Models via Adaptive Feature Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wang, Fei Shen, Jun Zhang, Kuan Tian, Qing Gu, Yonghang Guan, Zhiwei Jiang","submitted_at":"2024-05-27T11:55:35Z","abstract_excerpt":"The success of the text-guided diffusion model has inspired the development and release of numerous powerful diffusion models within the open-source community. These models are typically fine-tuned on various expert datasets, showcasing diverse denoising capabilities. Leveraging multiple high-quality models to produce stronger generation ability is valuable, but has not been extensively studied. Existing methods primarily adopt parameter merging strategies to produce a new static model. However, they overlook the fact that the divergent denoising capabilities of the models may dynamically chan"},"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":"2405.17082","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T11:55:35Z","cross_cats_sorted":[],"title_canon_sha256":"b1f0bb9956efef9aafb6c2b597c0071f339253dc97cf2348bc0260c3cbbcbddc","abstract_canon_sha256":"60df1ed2bc23d46eda75b023696d3312f51df35d40c8a74731774ed7d3f16694"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:37.448338Z","signature_b64":"yGyiA5h1jQwGk/bGObk1bgz49P66fBkpOJeZUC2p1Tq7lJQolGFkodRD9GweKXX8q9lRhtQeCCMQr5wKHrAECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b1f60776cd5660bb58fbf852455384adc1d73384aeed5a35ecf8d0337cd972d","last_reissued_at":"2026-07-05T10:18:37.447809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:37.447809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensembling Diffusion Models via Adaptive Feature Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wang, Fei Shen, Jun Zhang, Kuan Tian, Qing Gu, Yonghang Guan, Zhiwei Jiang","submitted_at":"2024-05-27T11:55:35Z","abstract_excerpt":"The success of the text-guided diffusion model has inspired the development and release of numerous powerful diffusion models within the open-source community. These models are typically fine-tuned on various expert datasets, showcasing diverse denoising capabilities. Leveraging multiple high-quality models to produce stronger generation ability is valuable, but has not been extensively studied. Existing methods primarily adopt parameter merging strategies to produce a new static model. However, they overlook the fact that the divergent denoising capabilities of the models may dynamically chan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17082","kind":"arxiv","version":2},"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/2405.17082/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":"2405.17082","created_at":"2026-07-05T10:18:37.447870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17082v2","created_at":"2026-07-05T10:18:37.447870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17082","created_at":"2026-07-05T10:18:37.447870+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMPWA53M2VTA","created_at":"2026-07-05T10:18:37.447870+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMPWA53M2VTAXNMP","created_at":"2026-07-05T10:18:37.447870+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMPWA53M","created_at":"2026-07-05T10:18:37.447870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13311","citing_title":"FashionPose: Unified Text-Driven Fashion Synthesis with Joint Geometric and Photometric Control","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMPWA53M2VTAXNMPX6CSIVJYJL","json":"https://pith.science/pith/DMPWA53M2VTAXNMPX6CSIVJYJL.json","graph_json":"https://pith.science/api/pith-number/DMPWA53M2VTAXNMPX6CSIVJYJL/graph.json","events_json":"https://pith.science/api/pith-number/DMPWA53M2VTAXNMPX6CSIVJYJL/events.json","paper":"https://pith.science/paper/DMPWA53M"},"agent_actions":{"view_html":"https://pith.science/pith/DMPWA53M2VTAXNMPX6CSIVJYJL","download_json":"https://pith.science/pith/DMPWA53M2VTAXNMPX6CSIVJYJL.json","view_paper":"https://pith.science/paper/DMPWA53M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17082&json=true","fetch_graph":"https://pith.science/api/pith-number/DMPWA53M2VTAXNMPX6CSIVJYJL/graph.json","fetch_events":"https://pith.science/api/pith-number/DMPWA53M2VTAXNMPX6CSIVJYJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMPWA53M2VTAXNMPX6CSIVJYJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMPWA53M2VTAXNMPX6CSIVJYJL/action/storage_attestation","attest_author":"https://pith.science/pith/DMPWA53M2VTAXNMPX6CSIVJYJL/action/author_attestation","sign_citation":"https://pith.science/pith/DMPWA53M2VTAXNMPX6CSIVJYJL/action/citation_signature","submit_replication":"https://pith.science/pith/DMPWA53M2VTAXNMPX6CSIVJYJL/action/replication_record"}},"created_at":"2026-07-05T10:18:37.447870+00:00","updated_at":"2026-07-05T10:18:37.447870+00:00"}