{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:72SCPPF3CKZRJRQIOAVLPQGZ2I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f54a41c5b2f8dc9ad34b8b0afd10ea777d39b401740db574ee25f54277df3699","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T12:23:58Z","title_canon_sha256":"5cc9738b10e9594625653099d289d4e6cfb56a2dfa9b0ff525e726bb5c5961fc"},"schema_version":"1.0","source":{"id":"2505.11178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11178","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11178v1","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11178","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"72SCPPF3CKZR","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"72SCPPF3CKZRJRQI","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"72SCPPF3","created_at":"2026-07-05T11:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:5667d24e978d5d3e3dfa20c1bbd3c351876b1a364823aa5b27945ebbdef528bb","target":"graph","created_at":"2026-07-05T11:04:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.11178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art T2I models are capable of generating high-resolution images given textual prompts. However, they still struggle with accurately depicting compositional scenes that specify multiple objects, attributes, and spatial relations. We present CompAlign, a challenging benchmark with an emphasis on assessing the depiction of 3D-spatial relationships, for evaluating and improving models on compositional image generation. CompAlign consists of 900 complex multi-subject image generation prompts that combine numerical and 3D-spatial relationships with varied attribute bindings. Our benchma","authors_text":"Kai-Wei Chang, Yixin Wan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T12:23:58Z","title":"CompAlign: Improving Compositional Text-to-Image Generation with a Complex Benchmark and Fine-Grained Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11178","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5502eea810b3bb229b8fabed0963c58735752e2cc97958c69b67c0419ff1429f","target":"record","created_at":"2026-07-05T11:04:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f54a41c5b2f8dc9ad34b8b0afd10ea777d39b401740db574ee25f54277df3699","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T12:23:58Z","title_canon_sha256":"5cc9738b10e9594625653099d289d4e6cfb56a2dfa9b0ff525e726bb5c5961fc"},"schema_version":"1.0","source":{"id":"2505.11178","kind":"arxiv","version":1}},"canonical_sha256":"fea427bcbb12b314c608702ab7c0d9d22649bd1ddd31945b2c8c5306942f1f38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fea427bcbb12b314c608702ab7c0d9d22649bd1ddd31945b2c8c5306942f1f38","first_computed_at":"2026-07-05T11:04:12.149139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:12.149139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8VupvurrrlIXeiXxEqxsvovsvoc+h1CYa1WvL8JdWos0yDqSM9JLEhG9ujKj/DUQo2NbxVv7q9yBl6V441gMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:12.149596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5502eea810b3bb229b8fabed0963c58735752e2cc97958c69b67c0419ff1429f","sha256:5667d24e978d5d3e3dfa20c1bbd3c351876b1a364823aa5b27945ebbdef528bb"],"state_sha256":"7fd0d37653edcb2ca9de8d543b0cf7f8074dc5557c18505b19126fe7484eb64d"}