{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CNPKZWJASSRWBVT4PHAQZ2C5PE","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":"239fd012f0bd69e31fd867f3aaeaf3ba59331933256b3b7bb88b88d60db11b97","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T18:36:33Z","title_canon_sha256":"2059af04c1c6f8eb7e8aef481ad3f7086392b7c68c4761882505c0ca5841af82"},"schema_version":"1.0","source":{"id":"2506.05501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05501","created_at":"2026-07-05T11:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05501v1","created_at":"2026-07-05T11:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05501","created_at":"2026-07-05T11:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"CNPKZWJASSRW","created_at":"2026-07-05T11:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"CNPKZWJASSRWBVT4","created_at":"2026-07-05T11:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"CNPKZWJA","created_at":"2026-07-05T11:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:ee473403f3bcc48e6f04804b98b9010821aa9668a63391e84bb93e76af6a3ca5","target":"graph","created_at":"2026-07-05T11:17:03Z","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/2506.05501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but different fine-grained semantics -- reveals that existing models struggle with fine-grained text-image alignment thus failing to realize precise control over visual tokens. To address this, we propose FocusDiff, which enhances fine-grained text-image semantic alignment by focusing on subtle differences between similar text-image pairs. We construct a new dataset ","authors_text":"Hang Zhao, Juncheng Li, Kaihang Pan, Kai Shen, Siliang Tang, Wendong Bu, Yang Wu, Yueting Zhuang, Yunfei Li, Yuruo Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T18:36:33Z","title":"FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05501","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":"sha256:39e44186313f3f6d0a2e40b76e4b004b17efccf0a9176a570f3cb3850134434f","target":"record","created_at":"2026-07-05T11:17:03Z","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":"239fd012f0bd69e31fd867f3aaeaf3ba59331933256b3b7bb88b88d60db11b97","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T18:36:33Z","title_canon_sha256":"2059af04c1c6f8eb7e8aef481ad3f7086392b7c68c4761882505c0ca5841af82"},"schema_version":"1.0","source":{"id":"2506.05501","kind":"arxiv","version":1}},"canonical_sha256":"135eacd92094a360d67c79c10ce85d7923a2e823b429dc9236fc5b20555bc252","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"135eacd92094a360d67c79c10ce85d7923a2e823b429dc9236fc5b20555bc252","first_computed_at":"2026-07-05T11:17:03.893785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:03.893785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"knF+pGXtoDBU2Suzj+sCVEv1RTMIKMTA33dVowEosIdz1yEHg4ZGsZfjoC9zwLP0U/cdH+caJOil6R2wdmM6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:03.894284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39e44186313f3f6d0a2e40b76e4b004b17efccf0a9176a570f3cb3850134434f","sha256:ee473403f3bcc48e6f04804b98b9010821aa9668a63391e84bb93e76af6a3ca5"],"state_sha256":"e0eeb25419849ef404e6a40092ca69253f9208b4617fac6a2dbe98f6b6d65d5c"}