{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KWLAVYPDZ77WEHCZWXYR7ZVMIB","short_pith_number":"pith:KWLAVYPD","schema_version":"1.0","canonical_sha256":"55960ae1e3cfff621c59b5f11fe6ac40465f3a034ca91965f7bcbc82ad350d1f","source":{"kind":"arxiv","id":"2505.06890","version":1},"attestation_state":"computed","paper":{"title":"Image Classification Using a Diffusion Model as a Pre-Training Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Kosuke Ukita, Tsuyoshi Okita, Ye Xiaolong","submitted_at":"2025-05-11T08:03:18Z","abstract_excerpt":"In this paper, we propose a diffusion model that integrates a representation-conditioning mechanism, where the representations derived from a Vision Transformer (ViT) are used to condition the internal process of a Transformer-based diffusion model. This approach enables representation-conditioned data generation, addressing the challenge of requiring large-scale labeled datasets by leveraging self-supervised learning on unlabeled data. We evaluate our method through a zero-shot classification task for hematoma detection in brain imaging. Compared to the strong contrastive learning baseline, D"},"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":"2505.06890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-11T08:03:18Z","cross_cats_sorted":["cs.CV","eess.IV"],"title_canon_sha256":"04f3ae8cf481c997072ec01d6334aa27cfc69f9418ee1edd9775e88b83fe6d6f","abstract_canon_sha256":"c300366dd0d792d1aa3dc74b6f09675906c13ed27b743c319863506c0f87b54d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:38.563104Z","signature_b64":"1k4RGpCoQjztEODm5rAP5JKkBGovSzGu4wsjbjQv/2Cmji/dxttfWdlNFXiAdhjiZK8dB11OdXvuutS8y+phBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55960ae1e3cfff621c59b5f11fe6ac40465f3a034ca91965f7bcbc82ad350d1f","last_reissued_at":"2026-07-05T11:01:38.562601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:38.562601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Classification Using a Diffusion Model as a Pre-Training Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Kosuke Ukita, Tsuyoshi Okita, Ye Xiaolong","submitted_at":"2025-05-11T08:03:18Z","abstract_excerpt":"In this paper, we propose a diffusion model that integrates a representation-conditioning mechanism, where the representations derived from a Vision Transformer (ViT) are used to condition the internal process of a Transformer-based diffusion model. This approach enables representation-conditioned data generation, addressing the challenge of requiring large-scale labeled datasets by leveraging self-supervised learning on unlabeled data. We evaluate our method through a zero-shot classification task for hematoma detection in brain imaging. Compared to the strong contrastive learning baseline, D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06890","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/2505.06890/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":"2505.06890","created_at":"2026-07-05T11:01:38.562665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06890v1","created_at":"2026-07-05T11:01:38.562665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06890","created_at":"2026-07-05T11:01:38.562665+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWLAVYPDZ77W","created_at":"2026-07-05T11:01:38.562665+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWLAVYPDZ77WEHCZ","created_at":"2026-07-05T11:01:38.562665+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWLAVYPD","created_at":"2026-07-05T11:01:38.562665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWLAVYPDZ77WEHCZWXYR7ZVMIB","json":"https://pith.science/pith/KWLAVYPDZ77WEHCZWXYR7ZVMIB.json","graph_json":"https://pith.science/api/pith-number/KWLAVYPDZ77WEHCZWXYR7ZVMIB/graph.json","events_json":"https://pith.science/api/pith-number/KWLAVYPDZ77WEHCZWXYR7ZVMIB/events.json","paper":"https://pith.science/paper/KWLAVYPD"},"agent_actions":{"view_html":"https://pith.science/pith/KWLAVYPDZ77WEHCZWXYR7ZVMIB","download_json":"https://pith.science/pith/KWLAVYPDZ77WEHCZWXYR7ZVMIB.json","view_paper":"https://pith.science/paper/KWLAVYPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06890&json=true","fetch_graph":"https://pith.science/api/pith-number/KWLAVYPDZ77WEHCZWXYR7ZVMIB/graph.json","fetch_events":"https://pith.science/api/pith-number/KWLAVYPDZ77WEHCZWXYR7ZVMIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWLAVYPDZ77WEHCZWXYR7ZVMIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWLAVYPDZ77WEHCZWXYR7ZVMIB/action/storage_attestation","attest_author":"https://pith.science/pith/KWLAVYPDZ77WEHCZWXYR7ZVMIB/action/author_attestation","sign_citation":"https://pith.science/pith/KWLAVYPDZ77WEHCZWXYR7ZVMIB/action/citation_signature","submit_replication":"https://pith.science/pith/KWLAVYPDZ77WEHCZWXYR7ZVMIB/action/replication_record"}},"created_at":"2026-07-05T11:01:38.562665+00:00","updated_at":"2026-07-05T11:01:38.562665+00:00"}