{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:47ODAVXDD6RRYFWEHGWHFMSQFR","short_pith_number":"pith:47ODAVXD","schema_version":"1.0","canonical_sha256":"e7dc3056e31fa31c16c439ac72b2502c5703bb9b2dcc4b01c89fa2e499ee00df","source":{"kind":"arxiv","id":"2206.01714","version":6},"attestation_state":"computed","paper":{"title":"Compositional Visual Generation with Composable Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Joshua B. Tenenbaum, Nan Liu, Shuang Li, Yilun Du","submitted_at":"2022-06-03T17:47:04Z","abstract_excerpt":"Large text-guided diffusion models, such as DALLE-2, are able to generate stunning photorealistic images given natural language descriptions. While such models are highly flexible, they struggle to understand the composition of certain concepts, such as confusing the attributes of different objects or relations between objects. In this paper, we propose an alternative structured approach for compositional generation using diffusion models. An image is generated by composing a set of diffusion models, with each of them modeling a certain component of the image. To do this, we interpret diffusio"},"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":"2206.01714","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-03T17:47:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8d625e6349184b5cd6d82eeada0bcbda8bbb6a020125cd3d64d874d478a2818c","abstract_canon_sha256":"08101a060368fa170605eefa3628781a083bf5b999ee1d0268d84df9bffb308b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:12.151811Z","signature_b64":"N3LBjM14VckX8u7LniFzxTNpaUtoQwxysJJiLKKJzl25iojMqcEWWGJCpOK2WJWkusqS82Qfc7b9p8ZIhZ+xBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7dc3056e31fa31c16c439ac72b2502c5703bb9b2dcc4b01c89fa2e499ee00df","last_reissued_at":"2026-07-05T05:33:12.151286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:12.151286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Visual Generation with Composable Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Joshua B. Tenenbaum, Nan Liu, Shuang Li, Yilun Du","submitted_at":"2022-06-03T17:47:04Z","abstract_excerpt":"Large text-guided diffusion models, such as DALLE-2, are able to generate stunning photorealistic images given natural language descriptions. While such models are highly flexible, they struggle to understand the composition of certain concepts, such as confusing the attributes of different objects or relations between objects. In this paper, we propose an alternative structured approach for compositional generation using diffusion models. An image is generated by composing a set of diffusion models, with each of them modeling a certain component of the image. To do this, we interpret diffusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01714","kind":"arxiv","version":6},"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/2206.01714/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":"2206.01714","created_at":"2026-07-05T05:33:12.151361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.01714v6","created_at":"2026-07-05T05:33:12.151361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01714","created_at":"2026-07-05T05:33:12.151361+00:00"},{"alias_kind":"pith_short_12","alias_value":"47ODAVXDD6RR","created_at":"2026-07-05T05:33:12.151361+00:00"},{"alias_kind":"pith_short_16","alias_value":"47ODAVXDD6RRYFWE","created_at":"2026-07-05T05:33:12.151361+00:00"},{"alias_kind":"pith_short_8","alias_value":"47ODAVXD","created_at":"2026-07-05T05:33:12.151361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27123","citing_title":"Proposal-Conditioned Latent Diffusion for Closed-Loop Traffic Scenario Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23468","citing_title":"Multi-Modal Manipulation via Multi-Modal Policy Consensus","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23748","citing_title":"A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2302.12192","citing_title":"Aligning Text-to-Image Models using Human Feedback","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2305.14325","citing_title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23536","citing_title":"$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2305.13301","citing_title":"Training Diffusion Models with Reinforcement Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02583","citing_title":"Stylistic Attribute Control in Latent Diffusion Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47ODAVXDD6RRYFWEHGWHFMSQFR","json":"https://pith.science/pith/47ODAVXDD6RRYFWEHGWHFMSQFR.json","graph_json":"https://pith.science/api/pith-number/47ODAVXDD6RRYFWEHGWHFMSQFR/graph.json","events_json":"https://pith.science/api/pith-number/47ODAVXDD6RRYFWEHGWHFMSQFR/events.json","paper":"https://pith.science/paper/47ODAVXD"},"agent_actions":{"view_html":"https://pith.science/pith/47ODAVXDD6RRYFWEHGWHFMSQFR","download_json":"https://pith.science/pith/47ODAVXDD6RRYFWEHGWHFMSQFR.json","view_paper":"https://pith.science/paper/47ODAVXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.01714&json=true","fetch_graph":"https://pith.science/api/pith-number/47ODAVXDD6RRYFWEHGWHFMSQFR/graph.json","fetch_events":"https://pith.science/api/pith-number/47ODAVXDD6RRYFWEHGWHFMSQFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47ODAVXDD6RRYFWEHGWHFMSQFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47ODAVXDD6RRYFWEHGWHFMSQFR/action/storage_attestation","attest_author":"https://pith.science/pith/47ODAVXDD6RRYFWEHGWHFMSQFR/action/author_attestation","sign_citation":"https://pith.science/pith/47ODAVXDD6RRYFWEHGWHFMSQFR/action/citation_signature","submit_replication":"https://pith.science/pith/47ODAVXDD6RRYFWEHGWHFMSQFR/action/replication_record"}},"created_at":"2026-07-05T05:33:12.151361+00:00","updated_at":"2026-07-05T05:33:12.151361+00:00"}