{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4GC7AQMPE4ID7LPOAYORCZESBZ","short_pith_number":"pith:4GC7AQMP","schema_version":"1.0","canonical_sha256":"e185f0418f27103fadee061d1164920e7d87c47e77e8bd7f293f135db0a5555c","source":{"kind":"arxiv","id":"2311.14542","version":2},"attestation_state":"computed","paper":{"title":"ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schr\\\"odinger Bridge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eslam Abdelrahman, Liangbing Zhao, Matthieu Cord, Mohamed Elhoseiny, Patrick Perez, Vincent Tao Hu","submitted_at":"2023-11-24T15:20:01Z","abstract_excerpt":"Diffusion models break down the challenging task of generating data from high-dimensional distributions into a series of easier denoising steps. Inspired by this paradigm, we propose a novel approach that extends the diffusion framework into modality space, decomposing the complex task of RGB image generation into simpler, interpretable stages. Our method, termed ToddlerDiffusion, cascades modality-specific models, each responsible for generating an intermediate representation, such as contours, palettes, and detailed textures, ultimately culminating in a high-quality RGB image. Instead of rel"},"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":"2311.14542","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-24T15:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"287920cd4fb766c8b2e39ce18fcdc43b4241e3986c161bf52f7999839d70fe94","abstract_canon_sha256":"e96adbaf8ed6783753d227602a3f1360ac1a189a5514f9bb017cbee5412fc28e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:10.310477Z","signature_b64":"E6WxPYWYVhR/eeU/Z7WiFyR2cy93xbTtPVT2A/2ZCFsqvtSGsiFO9yWJF1VqgaZdOybovR0yyNUgWyaUu9pxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e185f0418f27103fadee061d1164920e7d87c47e77e8bd7f293f135db0a5555c","last_reissued_at":"2026-07-05T09:16:10.309898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:10.309898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schr\\\"odinger Bridge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eslam Abdelrahman, Liangbing Zhao, Matthieu Cord, Mohamed Elhoseiny, Patrick Perez, Vincent Tao Hu","submitted_at":"2023-11-24T15:20:01Z","abstract_excerpt":"Diffusion models break down the challenging task of generating data from high-dimensional distributions into a series of easier denoising steps. Inspired by this paradigm, we propose a novel approach that extends the diffusion framework into modality space, decomposing the complex task of RGB image generation into simpler, interpretable stages. Our method, termed ToddlerDiffusion, cascades modality-specific models, each responsible for generating an intermediate representation, such as contours, palettes, and detailed textures, ultimately culminating in a high-quality RGB image. Instead of rel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14542","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/2311.14542/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":"2311.14542","created_at":"2026-07-05T09:16:10.309971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14542v2","created_at":"2026-07-05T09:16:10.309971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14542","created_at":"2026-07-05T09:16:10.309971+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GC7AQMPE4ID","created_at":"2026-07-05T09:16:10.309971+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GC7AQMPE4ID7LPO","created_at":"2026-07-05T09:16:10.309971+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GC7AQMP","created_at":"2026-07-05T09:16:10.309971+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/4GC7AQMPE4ID7LPOAYORCZESBZ","json":"https://pith.science/pith/4GC7AQMPE4ID7LPOAYORCZESBZ.json","graph_json":"https://pith.science/api/pith-number/4GC7AQMPE4ID7LPOAYORCZESBZ/graph.json","events_json":"https://pith.science/api/pith-number/4GC7AQMPE4ID7LPOAYORCZESBZ/events.json","paper":"https://pith.science/paper/4GC7AQMP"},"agent_actions":{"view_html":"https://pith.science/pith/4GC7AQMPE4ID7LPOAYORCZESBZ","download_json":"https://pith.science/pith/4GC7AQMPE4ID7LPOAYORCZESBZ.json","view_paper":"https://pith.science/paper/4GC7AQMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14542&json=true","fetch_graph":"https://pith.science/api/pith-number/4GC7AQMPE4ID7LPOAYORCZESBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4GC7AQMPE4ID7LPOAYORCZESBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GC7AQMPE4ID7LPOAYORCZESBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GC7AQMPE4ID7LPOAYORCZESBZ/action/storage_attestation","attest_author":"https://pith.science/pith/4GC7AQMPE4ID7LPOAYORCZESBZ/action/author_attestation","sign_citation":"https://pith.science/pith/4GC7AQMPE4ID7LPOAYORCZESBZ/action/citation_signature","submit_replication":"https://pith.science/pith/4GC7AQMPE4ID7LPOAYORCZESBZ/action/replication_record"}},"created_at":"2026-07-05T09:16:10.309971+00:00","updated_at":"2026-07-05T09:16:10.309971+00:00"}