{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CGNA5LMCZYI3TXV3UJGO4KME7C","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":"443ff4e3704d11ec80cb340707eeafa8c4c114280b1bd1c7e9b045445faa6798","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T14:17:05Z","title_canon_sha256":"8534f1e13acfe3c2b3790c08ce422f7e9c128ec3a77611286f27456b402517ec"},"schema_version":"1.0","source":{"id":"2606.31711","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31711","created_at":"2026-07-01T01:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31711v1","created_at":"2026-07-01T01:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31711","created_at":"2026-07-01T01:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"CGNA5LMCZYI3","created_at":"2026-07-01T01:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"CGNA5LMCZYI3TXV3","created_at":"2026-07-01T01:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"CGNA5LMC","created_at":"2026-07-01T01:18:12Z"}],"graph_snapshots":[{"event_id":"sha256:f272e39fa12bcf12865cb3d8059c1c7baf045abd4fc28aa600428743632f4f46","target":"graph","created_at":"2026-07-01T01:18:12Z","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/2606.31711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Faithfulness -- how precisely a generated image aligns with its prompt -- is increasingly central to the real-world utility of text-to-image (T2I) models. Existing faithfulness benchmarks, however, rely on simple atomic instructions, on which top-tier systems already achieve near-perfect scores. As T2I models enter creative workflows, users issue multi-faceted requests combining intricate spatial relationships, stylistic constraints, and complex text rendering. In this setting, a single binary VLM-judge score no longer captures which specific constraints the model fails to satisfy. We introduc","authors_text":"Cho-Jui Hsieh, Evan Frick, I-Hung Hsu, Ion Stoica, Sohyun An, Tong Xie, Wei-Lin Chiang, Yuanhao Ban, Yunqi Hong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T14:17:05Z","title":"Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31711","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":"sha256:5df1ff0544988620f61a732f68e4a2cb9ea3cd798b89eb517c3ec0807b901235","target":"record","created_at":"2026-07-01T01:18:12Z","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":"443ff4e3704d11ec80cb340707eeafa8c4c114280b1bd1c7e9b045445faa6798","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T14:17:05Z","title_canon_sha256":"8534f1e13acfe3c2b3790c08ce422f7e9c128ec3a77611286f27456b402517ec"},"schema_version":"1.0","source":{"id":"2606.31711","kind":"arxiv","version":1}},"canonical_sha256":"119a0ead82ce11b9debba24cee2984f8ac0d494dfde83d41e3e3d630ea61663e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"119a0ead82ce11b9debba24cee2984f8ac0d494dfde83d41e3e3d630ea61663e","first_computed_at":"2026-07-01T01:18:12.480759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:12.480759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M9OApho4guYPWTxSQgbylsDC/1jx2MTmZr4RoNo8nV35sxZx3Cea5qhaTdKRNWI2Ue3+IWaHD9/zt60jvH/5AQ==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:12.481200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31711","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5df1ff0544988620f61a732f68e4a2cb9ea3cd798b89eb517c3ec0807b901235","sha256:f272e39fa12bcf12865cb3d8059c1c7baf045abd4fc28aa600428743632f4f46"],"state_sha256":"4b9b4e4f454c73c279f7a7866fd5d536ea5a95a2966f0dffa9e02622ae23dc9f"}