{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BRKBX4AJNQBB4MEDW2JWD4QEEH","short_pith_number":"pith:BRKBX4AJ","schema_version":"1.0","canonical_sha256":"0c541bf0096c021e3083b69361f20421f5e0b2d08dcb7ca6ff9a201ff4855128","source":{"kind":"arxiv","id":"2605.27343","version":1},"attestation_state":"computed","paper":{"title":"Towards Controllable Image Generation through Representation-Conditioned Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gabriel Eilertsen, Jonas Unger, Nithesh Chandher Karthikeyan","submitted_at":"2026-05-26T17:46:25Z","abstract_excerpt":"Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated datasets. In this preliminary work, we explore diffusion models conditioned on representations from a pre-trained self-supervised model. The self-conditioning mechanism not only improves the quality of unconditional image generation, but also provides a representation space that can be used to cont"},"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":"2605.27343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T17:46:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0798e9e279fc2903b94dc113adf2e1bc4d26cc34148e2a9ad64c8a430f13f7d5","abstract_canon_sha256":"d22e61e1231502159e72a3e0d5ddbfff3bb3ac517ec3eb5ea0a4c2f02c6746bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:18.944440Z","signature_b64":"qRAxtse94kNOIX7VoChipH6Ck/4XLz2SAkkbiGdxKR0DOv4TNkCApLtjNmxdBReSnzyu3ZnomP6LUbjqz2hRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c541bf0096c021e3083b69361f20421f5e0b2d08dcb7ca6ff9a201ff4855128","last_reissued_at":"2026-05-27T02:06:18.943623Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:18.943623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Controllable Image Generation through Representation-Conditioned Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gabriel Eilertsen, Jonas Unger, Nithesh Chandher Karthikeyan","submitted_at":"2026-05-26T17:46:25Z","abstract_excerpt":"Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated datasets. In this preliminary work, we explore diffusion models conditioned on representations from a pre-trained self-supervised model. The self-conditioning mechanism not only improves the quality of unconditional image generation, but also provides a representation space that can be used to cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27343","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/2605.27343/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":"2605.27343","created_at":"2026-05-27T02:06:18.943702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27343v1","created_at":"2026-05-27T02:06:18.943702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27343","created_at":"2026-05-27T02:06:18.943702+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRKBX4AJNQBB","created_at":"2026-05-27T02:06:18.943702+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRKBX4AJNQBB4MED","created_at":"2026-05-27T02:06:18.943702+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRKBX4AJ","created_at":"2026-05-27T02:06:18.943702+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/BRKBX4AJNQBB4MEDW2JWD4QEEH","json":"https://pith.science/pith/BRKBX4AJNQBB4MEDW2JWD4QEEH.json","graph_json":"https://pith.science/api/pith-number/BRKBX4AJNQBB4MEDW2JWD4QEEH/graph.json","events_json":"https://pith.science/api/pith-number/BRKBX4AJNQBB4MEDW2JWD4QEEH/events.json","paper":"https://pith.science/paper/BRKBX4AJ"},"agent_actions":{"view_html":"https://pith.science/pith/BRKBX4AJNQBB4MEDW2JWD4QEEH","download_json":"https://pith.science/pith/BRKBX4AJNQBB4MEDW2JWD4QEEH.json","view_paper":"https://pith.science/paper/BRKBX4AJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27343&json=true","fetch_graph":"https://pith.science/api/pith-number/BRKBX4AJNQBB4MEDW2JWD4QEEH/graph.json","fetch_events":"https://pith.science/api/pith-number/BRKBX4AJNQBB4MEDW2JWD4QEEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRKBX4AJNQBB4MEDW2JWD4QEEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRKBX4AJNQBB4MEDW2JWD4QEEH/action/storage_attestation","attest_author":"https://pith.science/pith/BRKBX4AJNQBB4MEDW2JWD4QEEH/action/author_attestation","sign_citation":"https://pith.science/pith/BRKBX4AJNQBB4MEDW2JWD4QEEH/action/citation_signature","submit_replication":"https://pith.science/pith/BRKBX4AJNQBB4MEDW2JWD4QEEH/action/replication_record"}},"created_at":"2026-05-27T02:06:18.943702+00:00","updated_at":"2026-05-27T02:06:18.943702+00:00"}