{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BIFDJ6QQFTVVZUIXUY2D33OLYE","short_pith_number":"pith:BIFDJ6QQ","schema_version":"1.0","canonical_sha256":"0a0a34fa102ceb5cd117a6343dedcbc113219f977793b47b28feb4c6663c196e","source":{"kind":"arxiv","id":"2606.04479","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Reasoning Fidelity in Visual Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiajun Hong, Jiawei Zhou","submitted_at":"2026-06-03T05:53:58Z","abstract_excerpt":"Recent text-to-image (T2I) models can render highly legible and well-structured text within images, enabling applications including document generation and slide generation. However, it remains unclear whether such systems faithfully preserve reasoning ability when complex solutions must be expressed directly through rendered text, or whether they merely imitate surface-level patterns. We investigate this question by evaluating reasoning fidelity in visual text generation, where models must express complete reasoning processes as images. Our evaluation includes long text rendering, factual kno"},"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":"2606.04479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T05:53:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9e791a8368c185701511c759a96fef4f8e83525d611710b0302e37816663152c","abstract_canon_sha256":"ad088585a56b6fede1bb7f79d7abd35e900523f966621551d90410cef801b198"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:09.704003Z","signature_b64":"j7DW7+lnVqfL72NrThYKZaBYJqB7jEhZ16iF56RuDdI8x2VOcCcQePapNCu9njkVx5ITiQ6j1Y3nASfqrkFQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a0a34fa102ceb5cd117a6343dedcbc113219f977793b47b28feb4c6663c196e","last_reissued_at":"2026-06-04T01:09:09.703292Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:09.703292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Reasoning Fidelity in Visual Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiajun Hong, Jiawei Zhou","submitted_at":"2026-06-03T05:53:58Z","abstract_excerpt":"Recent text-to-image (T2I) models can render highly legible and well-structured text within images, enabling applications including document generation and slide generation. However, it remains unclear whether such systems faithfully preserve reasoning ability when complex solutions must be expressed directly through rendered text, or whether they merely imitate surface-level patterns. We investigate this question by evaluating reasoning fidelity in visual text generation, where models must express complete reasoning processes as images. Our evaluation includes long text rendering, factual kno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04479","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/2606.04479/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":"2606.04479","created_at":"2026-06-04T01:09:09.703414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04479v1","created_at":"2026-06-04T01:09:09.703414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04479","created_at":"2026-06-04T01:09:09.703414+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIFDJ6QQFTVV","created_at":"2026-06-04T01:09:09.703414+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIFDJ6QQFTVVZUIX","created_at":"2026-06-04T01:09:09.703414+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIFDJ6QQ","created_at":"2026-06-04T01:09:09.703414+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/BIFDJ6QQFTVVZUIXUY2D33OLYE","json":"https://pith.science/pith/BIFDJ6QQFTVVZUIXUY2D33OLYE.json","graph_json":"https://pith.science/api/pith-number/BIFDJ6QQFTVVZUIXUY2D33OLYE/graph.json","events_json":"https://pith.science/api/pith-number/BIFDJ6QQFTVVZUIXUY2D33OLYE/events.json","paper":"https://pith.science/paper/BIFDJ6QQ"},"agent_actions":{"view_html":"https://pith.science/pith/BIFDJ6QQFTVVZUIXUY2D33OLYE","download_json":"https://pith.science/pith/BIFDJ6QQFTVVZUIXUY2D33OLYE.json","view_paper":"https://pith.science/paper/BIFDJ6QQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04479&json=true","fetch_graph":"https://pith.science/api/pith-number/BIFDJ6QQFTVVZUIXUY2D33OLYE/graph.json","fetch_events":"https://pith.science/api/pith-number/BIFDJ6QQFTVVZUIXUY2D33OLYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIFDJ6QQFTVVZUIXUY2D33OLYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIFDJ6QQFTVVZUIXUY2D33OLYE/action/storage_attestation","attest_author":"https://pith.science/pith/BIFDJ6QQFTVVZUIXUY2D33OLYE/action/author_attestation","sign_citation":"https://pith.science/pith/BIFDJ6QQFTVVZUIXUY2D33OLYE/action/citation_signature","submit_replication":"https://pith.science/pith/BIFDJ6QQFTVVZUIXUY2D33OLYE/action/replication_record"}},"created_at":"2026-06-04T01:09:09.703414+00:00","updated_at":"2026-06-04T01:09:09.703414+00:00"}