{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6V6OVXHR422EU7NYD3EW5HQXII","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":"cbfc6371905a9dc59bf67c834f26d06e6aa18340f5b115bce2d457f10e7fdf38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T05:38:13Z","title_canon_sha256":"87275784ad844e3157941515995ae28440fa3af80dcd34dec5d9c4073a009431"},"schema_version":"1.0","source":{"id":"2505.03203","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03203","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03203v1","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03203","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"6V6OVXHR422E","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"pith_short_16","alias_value":"6V6OVXHR422EU7NY","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"pith_short_8","alias_value":"6V6OVXHR","created_at":"2026-07-05T10:59:12Z"}],"graph_snapshots":[{"event_id":"sha256:973415d295c16ce22a56e788c1d68684a944194847e6756b894dab828c95d81e","target":"graph","created_at":"2026-07-05T10:59:12Z","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/2505.03203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advanced diffusion models have made notable progress in text-to-image compositional generation. However, it is still a challenge for existing models to achieve text-image alignment when confronted with complex text prompts. In this work, we highlight two factors that affect this alignment: the quality of the randomly initialized noise and the reliability of the generated controlling mask. We then propose PiCo (Pick-and-Control), a novel training-free approach with two key components to tackle these two factors. First, we develop a noise selection module to assess the quality of the random nois","authors_text":"Chang Xie, Chenyi Zhuang, Pan Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T05:38:13Z","title":"PiCo: Enhancing Text-Image Alignment with Improved Noise Selection and Precise Mask Control in Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03203","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:b27208b206fbb8ec216e9978ab6ecb1d5e34a5fa449a85214974f8afa51d6a7d","target":"record","created_at":"2026-07-05T10:59:12Z","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":"cbfc6371905a9dc59bf67c834f26d06e6aa18340f5b115bce2d457f10e7fdf38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T05:38:13Z","title_canon_sha256":"87275784ad844e3157941515995ae28440fa3af80dcd34dec5d9c4073a009431"},"schema_version":"1.0","source":{"id":"2505.03203","kind":"arxiv","version":1}},"canonical_sha256":"f57ceadcf1e6b44a7db81ec96e9e1742027bd2fa8df47938b99abd7dfffa3536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f57ceadcf1e6b44a7db81ec96e9e1742027bd2fa8df47938b99abd7dfffa3536","first_computed_at":"2026-07-05T10:59:12.122634Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:12.122634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u7aF99mvqsdOEo66XFz/8DnXxiBEYtijlx8Ck7v3Q6nqXRESUyMKnlr4IIAqs1OkXr++s0oDWc5rIhc9fwtFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:12.123067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03203","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b27208b206fbb8ec216e9978ab6ecb1d5e34a5fa449a85214974f8afa51d6a7d","sha256:973415d295c16ce22a56e788c1d68684a944194847e6756b894dab828c95d81e"],"state_sha256":"5924da8a49fcafc79e000c890e512b9f645ca0029f630dab5b11b9d54d4ee04e"}