{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5FMXBTUCNXF2FTGH7IASQDLLT3","short_pith_number":"pith:5FMXBTUC","schema_version":"1.0","canonical_sha256":"e95970ce826dcba2ccc7fa01280d6b9efe3248d2a554d8cad73974e50c99b6cf","source":{"kind":"arxiv","id":"2312.08825","version":1},"attestation_state":"computed","paper":{"title":"Guided Diffusion from Self-Supervised Diffusion Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bjorn Ommer, Cees G. M. Snoek, Mathilde Caron, Vincent Tao Hu, Yuki M. Asano, Yunlu Chen","submitted_at":"2023-12-14T11:19:11Z","abstract_excerpt":"Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like DINO. However, recent studies have revealed that the feature representation derived from diffusion model itself is discriminative for numerous downstream tasks as well, which prompts us to propose a framework to extract guidance from, and specifically for, diffusion models. Our research has yielded several significant contributions. Firstly, the guidance sign"},"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":"2312.08825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T11:19:11Z","cross_cats_sorted":[],"title_canon_sha256":"dd4842d49b31531c7f19c460fb7b377af6ea87e910fe82150c2b373b78eff527","abstract_canon_sha256":"2e03c54c1fc5278a0eaa9393c97281b936c8393778875b7a745cba9d46cd4021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:10.340531Z","signature_b64":"F2JofiVE1obSyKHw7kXt//wY+9VlxhiQ6h5wDFqxrZV0jTNVWDoQVkMHhiZWBg72VXyEh1TzbSz4EscKufdaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e95970ce826dcba2ccc7fa01280d6b9efe3248d2a554d8cad73974e50c99b6cf","last_reissued_at":"2026-07-05T07:24:10.340038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:10.340038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guided Diffusion from Self-Supervised Diffusion Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bjorn Ommer, Cees G. M. Snoek, Mathilde Caron, Vincent Tao Hu, Yuki M. Asano, Yunlu Chen","submitted_at":"2023-12-14T11:19:11Z","abstract_excerpt":"Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like DINO. However, recent studies have revealed that the feature representation derived from diffusion model itself is discriminative for numerous downstream tasks as well, which prompts us to propose a framework to extract guidance from, and specifically for, diffusion models. Our research has yielded several significant contributions. Firstly, the guidance sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08825","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/2312.08825/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":"2312.08825","created_at":"2026-07-05T07:24:10.340095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08825v1","created_at":"2026-07-05T07:24:10.340095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08825","created_at":"2026-07-05T07:24:10.340095+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FMXBTUCNXF2","created_at":"2026-07-05T07:24:10.340095+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FMXBTUCNXF2FTGH","created_at":"2026-07-05T07:24:10.340095+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FMXBTUC","created_at":"2026-07-05T07:24:10.340095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11521","citing_title":"Continuous Adversarial Flow Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5FMXBTUCNXF2FTGH7IASQDLLT3","json":"https://pith.science/pith/5FMXBTUCNXF2FTGH7IASQDLLT3.json","graph_json":"https://pith.science/api/pith-number/5FMXBTUCNXF2FTGH7IASQDLLT3/graph.json","events_json":"https://pith.science/api/pith-number/5FMXBTUCNXF2FTGH7IASQDLLT3/events.json","paper":"https://pith.science/paper/5FMXBTUC"},"agent_actions":{"view_html":"https://pith.science/pith/5FMXBTUCNXF2FTGH7IASQDLLT3","download_json":"https://pith.science/pith/5FMXBTUCNXF2FTGH7IASQDLLT3.json","view_paper":"https://pith.science/paper/5FMXBTUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08825&json=true","fetch_graph":"https://pith.science/api/pith-number/5FMXBTUCNXF2FTGH7IASQDLLT3/graph.json","fetch_events":"https://pith.science/api/pith-number/5FMXBTUCNXF2FTGH7IASQDLLT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FMXBTUCNXF2FTGH7IASQDLLT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FMXBTUCNXF2FTGH7IASQDLLT3/action/storage_attestation","attest_author":"https://pith.science/pith/5FMXBTUCNXF2FTGH7IASQDLLT3/action/author_attestation","sign_citation":"https://pith.science/pith/5FMXBTUCNXF2FTGH7IASQDLLT3/action/citation_signature","submit_replication":"https://pith.science/pith/5FMXBTUCNXF2FTGH7IASQDLLT3/action/replication_record"}},"created_at":"2026-07-05T07:24:10.340095+00:00","updated_at":"2026-07-05T07:24:10.340095+00:00"}