{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M2D4NATM5KNNBESF7OC4OTMOEA","short_pith_number":"pith:M2D4NATM","schema_version":"1.0","canonical_sha256":"6687c6826cea9ad09245fb85c74d8e203cd40d6b506126b268f50d3216d9f0f6","source":{"kind":"arxiv","id":"2303.16187","version":2},"attestation_state":"computed","paper":{"title":"Visual Chain-of-Thought Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Frank Wood, William Harvey","submitted_at":"2023-03-28T17:53:06Z","abstract_excerpt":"Recent progress with conditional image diffusion models has been stunning, and this holds true whether we are speaking about models conditioned on a text description, a scene layout, or a sketch. Unconditional image diffusion models are also improving but lag behind, as do diffusion models which are conditioned on lower-dimensional features like class labels. We propose to close the gap between conditional and unconditional models using a two-stage sampling procedure. In the first stage we sample an embedding describing the semantic content of the image. In the second stage we sample the image"},"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":"2303.16187","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T17:53:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3635572e35b0aa9527d064c961e2381dd0bfdc1f0a0b29232b79f1b8329b21eb","abstract_canon_sha256":"92efa800d755faaaa40d69cecee6e488134686d3cc9157897bfcead3ccf4fe37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:03.010090Z","signature_b64":"h/5X9r2qyYOcW3VYlPPRZkYQ/7i/NwvHGjqtTO5k/WEo9PT9U6GFUZGkBds7p579XxJRLOdUq/uynVhbu88JCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6687c6826cea9ad09245fb85c74d8e203cd40d6b506126b268f50d3216d9f0f6","last_reissued_at":"2026-07-05T06:23:03.009675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:03.009675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Chain-of-Thought Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Frank Wood, William Harvey","submitted_at":"2023-03-28T17:53:06Z","abstract_excerpt":"Recent progress with conditional image diffusion models has been stunning, and this holds true whether we are speaking about models conditioned on a text description, a scene layout, or a sketch. Unconditional image diffusion models are also improving but lag behind, as do diffusion models which are conditioned on lower-dimensional features like class labels. We propose to close the gap between conditional and unconditional models using a two-stage sampling procedure. In the first stage we sample an embedding describing the semantic content of the image. In the second stage we sample the image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16187","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/2303.16187/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":"2303.16187","created_at":"2026-07-05T06:23:03.009728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16187v2","created_at":"2026-07-05T06:23:03.009728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16187","created_at":"2026-07-05T06:23:03.009728+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2D4NATM5KNN","created_at":"2026-07-05T06:23:03.009728+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2D4NATM5KNNBESF","created_at":"2026-07-05T06:23:03.009728+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2D4NATM","created_at":"2026-07-05T06:23:03.009728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.22020","citing_title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17800","citing_title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2D4NATM5KNNBESF7OC4OTMOEA","json":"https://pith.science/pith/M2D4NATM5KNNBESF7OC4OTMOEA.json","graph_json":"https://pith.science/api/pith-number/M2D4NATM5KNNBESF7OC4OTMOEA/graph.json","events_json":"https://pith.science/api/pith-number/M2D4NATM5KNNBESF7OC4OTMOEA/events.json","paper":"https://pith.science/paper/M2D4NATM"},"agent_actions":{"view_html":"https://pith.science/pith/M2D4NATM5KNNBESF7OC4OTMOEA","download_json":"https://pith.science/pith/M2D4NATM5KNNBESF7OC4OTMOEA.json","view_paper":"https://pith.science/paper/M2D4NATM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16187&json=true","fetch_graph":"https://pith.science/api/pith-number/M2D4NATM5KNNBESF7OC4OTMOEA/graph.json","fetch_events":"https://pith.science/api/pith-number/M2D4NATM5KNNBESF7OC4OTMOEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2D4NATM5KNNBESF7OC4OTMOEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2D4NATM5KNNBESF7OC4OTMOEA/action/storage_attestation","attest_author":"https://pith.science/pith/M2D4NATM5KNNBESF7OC4OTMOEA/action/author_attestation","sign_citation":"https://pith.science/pith/M2D4NATM5KNNBESF7OC4OTMOEA/action/citation_signature","submit_replication":"https://pith.science/pith/M2D4NATM5KNNBESF7OC4OTMOEA/action/replication_record"}},"created_at":"2026-07-05T06:23:03.009728+00:00","updated_at":"2026-07-05T06:23:03.009728+00:00"}