{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SEKCQF4X33NARPPJSNYQ46AMGO","short_pith_number":"pith:SEKCQF4X","schema_version":"1.0","canonical_sha256":"9114281797deda08bde993710e780c339f1c78e2ba4aeeb8ecd2803cd7709622","source":{"kind":"arxiv","id":"2505.24086","version":1},"attestation_state":"computed","paper":{"title":"ComposeAnything: Composite Object Priors for Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Shizhe Chen, Zeeshan Khan","submitted_at":"2025-05-30T00:13:36Z","abstract_excerpt":"Generating images from text involving complex and novel object arrangements remains a significant challenge for current text-to-image (T2I) models. Although prior layout-based methods improve object arrangements using spatial constraints with 2D layouts, they often struggle to capture 3D positioning and sacrifice quality and coherence. In this work, we introduce ComposeAnything, a novel framework for improving compositional image generation without retraining existing T2I models. Our approach first leverages the chain-of-thought reasoning abilities of LLMs to produce 2.5D semantic layouts from"},"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":"2505.24086","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T00:13:36Z","cross_cats_sorted":[],"title_canon_sha256":"81d101760516227f449cdc4570b71fd85f8e04cc3f9c92e437ba7eae12d80af3","abstract_canon_sha256":"c7b1418f030f66bd8f67b279bf1e9b9d8c36d0363dbecfc2994c5e5c3ece7d09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:41.392198Z","signature_b64":"WgcnsLOoIEF7xi1JimI7W5r2oHLE8Rn9bY6p2NBxzhP22xEZICOSVeo0wvfE2nE2Ay8Moc0qT1B6fIjDlwBBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9114281797deda08bde993710e780c339f1c78e2ba4aeeb8ecd2803cd7709622","last_reissued_at":"2026-07-05T11:12:41.391678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:41.391678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComposeAnything: Composite Object Priors for Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Shizhe Chen, Zeeshan Khan","submitted_at":"2025-05-30T00:13:36Z","abstract_excerpt":"Generating images from text involving complex and novel object arrangements remains a significant challenge for current text-to-image (T2I) models. Although prior layout-based methods improve object arrangements using spatial constraints with 2D layouts, they often struggle to capture 3D positioning and sacrifice quality and coherence. In this work, we introduce ComposeAnything, a novel framework for improving compositional image generation without retraining existing T2I models. Our approach first leverages the chain-of-thought reasoning abilities of LLMs to produce 2.5D semantic layouts from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24086","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/2505.24086/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":"2505.24086","created_at":"2026-07-05T11:12:41.391736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24086v1","created_at":"2026-07-05T11:12:41.391736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24086","created_at":"2026-07-05T11:12:41.391736+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEKCQF4X33NA","created_at":"2026-07-05T11:12:41.391736+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEKCQF4X33NARPPJ","created_at":"2026-07-05T11:12:41.391736+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEKCQF4X","created_at":"2026-07-05T11:12:41.391736+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/SEKCQF4X33NARPPJSNYQ46AMGO","json":"https://pith.science/pith/SEKCQF4X33NARPPJSNYQ46AMGO.json","graph_json":"https://pith.science/api/pith-number/SEKCQF4X33NARPPJSNYQ46AMGO/graph.json","events_json":"https://pith.science/api/pith-number/SEKCQF4X33NARPPJSNYQ46AMGO/events.json","paper":"https://pith.science/paper/SEKCQF4X"},"agent_actions":{"view_html":"https://pith.science/pith/SEKCQF4X33NARPPJSNYQ46AMGO","download_json":"https://pith.science/pith/SEKCQF4X33NARPPJSNYQ46AMGO.json","view_paper":"https://pith.science/paper/SEKCQF4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24086&json=true","fetch_graph":"https://pith.science/api/pith-number/SEKCQF4X33NARPPJSNYQ46AMGO/graph.json","fetch_events":"https://pith.science/api/pith-number/SEKCQF4X33NARPPJSNYQ46AMGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEKCQF4X33NARPPJSNYQ46AMGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEKCQF4X33NARPPJSNYQ46AMGO/action/storage_attestation","attest_author":"https://pith.science/pith/SEKCQF4X33NARPPJSNYQ46AMGO/action/author_attestation","sign_citation":"https://pith.science/pith/SEKCQF4X33NARPPJSNYQ46AMGO/action/citation_signature","submit_replication":"https://pith.science/pith/SEKCQF4X33NARPPJSNYQ46AMGO/action/replication_record"}},"created_at":"2026-07-05T11:12:41.391736+00:00","updated_at":"2026-07-05T11:12:41.391736+00:00"}