{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GTMUY7SOWLM474LEYT7UZ5P6F3","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":"e6858bb65f5511b56b74e7d0eb513c2a094324e742445aa5a79b740040f439fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T15:27:13Z","title_canon_sha256":"3fc00888807089c2c9467c93ae4a4d4290a8206bc1607e60694dceabd2dad1a1"},"schema_version":"1.0","source":{"id":"2605.28615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28615","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28615v1","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28615","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"GTMUY7SOWLM4","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"GTMUY7SOWLM474LE","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"GTMUY7SO","created_at":"2026-05-28T02:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:afd3bfa2736824ff4807842385f4c1bc17b5aa9ef6b643168cc9e3a04a6a2f4c","target":"graph","created_at":"2026-05-28T02:04:57Z","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/2605.28615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the rapid progress of text-to-image (T2I) models, generating images that accurately reflect complex compositional prompts (covering attribute bindings, object relationships, counting) still remains challenging. To address this, we propose BiDPO, a framework to enhance T2I model's capability of compositional text-to-image generation. We begin by introducing an carefully designed pipeline to construct a large-scale preference dataset, BiComp, with strictly quality control. Then, we extend Diffusion DPO to jointly optimize image and text preferences, which is shown to greatly effective in","authors_text":"Wujian Peng, Yitong Chen, Zhuohan Liu, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T15:27:13Z","title":"Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28615","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":"sha256:147ed9e7855f262e35bf2636b550c40eada340ce53dfe71d513589a678b58bc6","target":"record","created_at":"2026-05-28T02:04:57Z","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":"e6858bb65f5511b56b74e7d0eb513c2a094324e742445aa5a79b740040f439fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T15:27:13Z","title_canon_sha256":"3fc00888807089c2c9467c93ae4a4d4290a8206bc1607e60694dceabd2dad1a1"},"schema_version":"1.0","source":{"id":"2605.28615","kind":"arxiv","version":1}},"canonical_sha256":"34d94c7e4eb2d9cff164c4ff4cf5fe2ef678b10d0478f62adcc21dc1cf7162a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34d94c7e4eb2d9cff164c4ff4cf5fe2ef678b10d0478f62adcc21dc1cf7162a0","first_computed_at":"2026-05-28T02:04:57.828232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:57.828232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uNQ8Hj/Qr5/P3gRMIqZiJ9iopfCB76VarzWt12YucQx3fd4wMiRW0VlPVqNb4D5Q1qlk+C2jtuX1UfbAR+tzDQ==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:57.828675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:147ed9e7855f262e35bf2636b550c40eada340ce53dfe71d513589a678b58bc6","sha256:afd3bfa2736824ff4807842385f4c1bc17b5aa9ef6b643168cc9e3a04a6a2f4c"],"state_sha256":"1593ca59eaf5360e43d62c15a824d5f658a4aa0c763c03829dc73f705845c5b7"}