{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CGNA5LMCZYI3TXV3UJGO4KME7C","short_pith_number":"pith:CGNA5LMC","schema_version":"1.0","canonical_sha256":"119a0ead82ce11b9debba24cee2984f8ac0d494dfde83d41e3e3d630ea61663e","source":{"kind":"arxiv","id":"2606.31711","version":1},"attestation_state":"computed","paper":{"title":"Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cho-Jui Hsieh, Evan Frick, I-Hung Hsu, Ion Stoica, Sohyun An, Tong Xie, Wei-Lin Chiang, Yuanhao Ban, Yunqi Hong","submitted_at":"2026-06-30T14:17:05Z","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"},"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":"2606.31711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T14:17:05Z","cross_cats_sorted":[],"title_canon_sha256":"8534f1e13acfe3c2b3790c08ce422f7e9c128ec3a77611286f27456b402517ec","abstract_canon_sha256":"443ff4e3704d11ec80cb340707eeafa8c4c114280b1bd1c7e9b045445faa6798"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:12.481200Z","signature_b64":"M9OApho4guYPWTxSQgbylsDC/1jx2MTmZr4RoNo8nV35sxZx3Cea5qhaTdKRNWI2Ue3+IWaHD9/zt60jvH/5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"119a0ead82ce11b9debba24cee2984f8ac0d494dfde83d41e3e3d630ea61663e","last_reissued_at":"2026-07-01T01:18:12.480759Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:12.480759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cho-Jui Hsieh, Evan Frick, I-Hung Hsu, Ion Stoica, Sohyun An, Tong Xie, Wei-Lin Chiang, Yuanhao Ban, Yunqi Hong","submitted_at":"2026-06-30T14:17:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31711","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/2606.31711/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":"2606.31711","created_at":"2026-07-01T01:18:12.480816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31711v1","created_at":"2026-07-01T01:18:12.480816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31711","created_at":"2026-07-01T01:18:12.480816+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGNA5LMCZYI3","created_at":"2026-07-01T01:18:12.480816+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGNA5LMCZYI3TXV3","created_at":"2026-07-01T01:18:12.480816+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGNA5LMC","created_at":"2026-07-01T01:18:12.480816+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/CGNA5LMCZYI3TXV3UJGO4KME7C","json":"https://pith.science/pith/CGNA5LMCZYI3TXV3UJGO4KME7C.json","graph_json":"https://pith.science/api/pith-number/CGNA5LMCZYI3TXV3UJGO4KME7C/graph.json","events_json":"https://pith.science/api/pith-number/CGNA5LMCZYI3TXV3UJGO4KME7C/events.json","paper":"https://pith.science/paper/CGNA5LMC"},"agent_actions":{"view_html":"https://pith.science/pith/CGNA5LMCZYI3TXV3UJGO4KME7C","download_json":"https://pith.science/pith/CGNA5LMCZYI3TXV3UJGO4KME7C.json","view_paper":"https://pith.science/paper/CGNA5LMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31711&json=true","fetch_graph":"https://pith.science/api/pith-number/CGNA5LMCZYI3TXV3UJGO4KME7C/graph.json","fetch_events":"https://pith.science/api/pith-number/CGNA5LMCZYI3TXV3UJGO4KME7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGNA5LMCZYI3TXV3UJGO4KME7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGNA5LMCZYI3TXV3UJGO4KME7C/action/storage_attestation","attest_author":"https://pith.science/pith/CGNA5LMCZYI3TXV3UJGO4KME7C/action/author_attestation","sign_citation":"https://pith.science/pith/CGNA5LMCZYI3TXV3UJGO4KME7C/action/citation_signature","submit_replication":"https://pith.science/pith/CGNA5LMCZYI3TXV3UJGO4KME7C/action/replication_record"}},"created_at":"2026-07-01T01:18:12.480816+00:00","updated_at":"2026-07-01T01:18:12.480816+00:00"}