{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GTMUY7SOWLM474LEYT7UZ5P6F3","short_pith_number":"pith:GTMUY7SO","schema_version":"1.0","canonical_sha256":"34d94c7e4eb2d9cff164c4ff4cf5fe2ef678b10d0478f62adcc21dc1cf7162a0","source":{"kind":"arxiv","id":"2605.28615","version":1},"attestation_state":"computed","paper":{"title":"Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wujian Peng, Yitong Chen, Zhuohan Liu, Zuxuan Wu","submitted_at":"2026-05-27T15:27:13Z","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"},"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":"2605.28615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T15:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"3fc00888807089c2c9467c93ae4a4d4290a8206bc1607e60694dceabd2dad1a1","abstract_canon_sha256":"e6858bb65f5511b56b74e7d0eb513c2a094324e742445aa5a79b740040f439fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:57.828675Z","signature_b64":"uNQ8Hj/Qr5/P3gRMIqZiJ9iopfCB76VarzWt12YucQx3fd4wMiRW0VlPVqNb4D5Q1qlk+C2jtuX1UfbAR+tzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34d94c7e4eb2d9cff164c4ff4cf5fe2ef678b10d0478f62adcc21dc1cf7162a0","last_reissued_at":"2026-05-28T02:04:57.828232Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:57.828232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wujian Peng, Yitong Chen, Zhuohan Liu, Zuxuan Wu","submitted_at":"2026-05-27T15:27:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28615","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/2605.28615/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":"2605.28615","created_at":"2026-05-28T02:04:57.828305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28615v1","created_at":"2026-05-28T02:04:57.828305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28615","created_at":"2026-05-28T02:04:57.828305+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTMUY7SOWLM4","created_at":"2026-05-28T02:04:57.828305+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTMUY7SOWLM474LE","created_at":"2026-05-28T02:04:57.828305+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTMUY7SO","created_at":"2026-05-28T02:04:57.828305+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/GTMUY7SOWLM474LEYT7UZ5P6F3","json":"https://pith.science/pith/GTMUY7SOWLM474LEYT7UZ5P6F3.json","graph_json":"https://pith.science/api/pith-number/GTMUY7SOWLM474LEYT7UZ5P6F3/graph.json","events_json":"https://pith.science/api/pith-number/GTMUY7SOWLM474LEYT7UZ5P6F3/events.json","paper":"https://pith.science/paper/GTMUY7SO"},"agent_actions":{"view_html":"https://pith.science/pith/GTMUY7SOWLM474LEYT7UZ5P6F3","download_json":"https://pith.science/pith/GTMUY7SOWLM474LEYT7UZ5P6F3.json","view_paper":"https://pith.science/paper/GTMUY7SO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28615&json=true","fetch_graph":"https://pith.science/api/pith-number/GTMUY7SOWLM474LEYT7UZ5P6F3/graph.json","fetch_events":"https://pith.science/api/pith-number/GTMUY7SOWLM474LEYT7UZ5P6F3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTMUY7SOWLM474LEYT7UZ5P6F3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTMUY7SOWLM474LEYT7UZ5P6F3/action/storage_attestation","attest_author":"https://pith.science/pith/GTMUY7SOWLM474LEYT7UZ5P6F3/action/author_attestation","sign_citation":"https://pith.science/pith/GTMUY7SOWLM474LEYT7UZ5P6F3/action/citation_signature","submit_replication":"https://pith.science/pith/GTMUY7SOWLM474LEYT7UZ5P6F3/action/replication_record"}},"created_at":"2026-05-28T02:04:57.828305+00:00","updated_at":"2026-05-28T02:04:57.828305+00:00"}