{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D2N6MP5FUEJVPQ4JANR7S4MNBQ","short_pith_number":"pith:D2N6MP5F","schema_version":"1.0","canonical_sha256":"1e9be63fa5a11357c3890363f9718d0c0f742b8349d77641925590ce3dd2d2c8","source":{"kind":"arxiv","id":"2502.15412","version":1},"attestation_state":"computed","paper":{"title":"Textual-to-Visual Iterative Self-Verification for Slide Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Jiyang Qiu, Xinbei Ma, Yunqing Xu","submitted_at":"2025-02-21T12:21:09Z","abstract_excerpt":"Generating presentation slides is a time-consuming task that urgently requires automation. Due to their limited flexibility and lack of automated refinement mechanisms, existing autonomous LLM-based agents face constraints in real-world applicability. We decompose the task of generating missing presentation slides into two key components: content generation and layout generation, aligning with the typical process of creating academic slides. First, we introduce a content generation approach that enhances coherence and relevance by incorporating context from surrounding slides and leveraging se"},"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":"2502.15412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T12:21:09Z","cross_cats_sorted":[],"title_canon_sha256":"cd59d7b0e2e9e69ef3d7921205d0f1dd8bb8286aebabe4f41b9f0f65f2485019","abstract_canon_sha256":"f769d4dd0f0e4e343db8aac975a68552cba062eec2a2ca41a2f323da0e676c6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:01.436265Z","signature_b64":"b0wjUgQV0fOJIMm8ZaXk0+vitg3tTZsf5mOGAyV4AKhhWCi0KPdR3eQUFxwGDoE2QC2TdWivEgQd2mkUmOxADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e9be63fa5a11357c3890363f9718d0c0f742b8349d77641925590ce3dd2d2c8","last_reissued_at":"2026-07-05T10:18:01.435770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:01.435770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Textual-to-Visual Iterative Self-Verification for Slide Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Jiyang Qiu, Xinbei Ma, Yunqing Xu","submitted_at":"2025-02-21T12:21:09Z","abstract_excerpt":"Generating presentation slides is a time-consuming task that urgently requires automation. Due to their limited flexibility and lack of automated refinement mechanisms, existing autonomous LLM-based agents face constraints in real-world applicability. We decompose the task of generating missing presentation slides into two key components: content generation and layout generation, aligning with the typical process of creating academic slides. First, we introduce a content generation approach that enhances coherence and relevance by incorporating context from surrounding slides and leveraging se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15412","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/2502.15412/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":"2502.15412","created_at":"2026-07-05T10:18:01.435826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15412v1","created_at":"2026-07-05T10:18:01.435826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15412","created_at":"2026-07-05T10:18:01.435826+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2N6MP5FUEJV","created_at":"2026-07-05T10:18:01.435826+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2N6MP5FUEJVPQ4J","created_at":"2026-07-05T10:18:01.435826+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2N6MP5F","created_at":"2026-07-05T10:18:01.435826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00407","citing_title":"Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2N6MP5FUEJVPQ4JANR7S4MNBQ","json":"https://pith.science/pith/D2N6MP5FUEJVPQ4JANR7S4MNBQ.json","graph_json":"https://pith.science/api/pith-number/D2N6MP5FUEJVPQ4JANR7S4MNBQ/graph.json","events_json":"https://pith.science/api/pith-number/D2N6MP5FUEJVPQ4JANR7S4MNBQ/events.json","paper":"https://pith.science/paper/D2N6MP5F"},"agent_actions":{"view_html":"https://pith.science/pith/D2N6MP5FUEJVPQ4JANR7S4MNBQ","download_json":"https://pith.science/pith/D2N6MP5FUEJVPQ4JANR7S4MNBQ.json","view_paper":"https://pith.science/paper/D2N6MP5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15412&json=true","fetch_graph":"https://pith.science/api/pith-number/D2N6MP5FUEJVPQ4JANR7S4MNBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/D2N6MP5FUEJVPQ4JANR7S4MNBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2N6MP5FUEJVPQ4JANR7S4MNBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2N6MP5FUEJVPQ4JANR7S4MNBQ/action/storage_attestation","attest_author":"https://pith.science/pith/D2N6MP5FUEJVPQ4JANR7S4MNBQ/action/author_attestation","sign_citation":"https://pith.science/pith/D2N6MP5FUEJVPQ4JANR7S4MNBQ/action/citation_signature","submit_replication":"https://pith.science/pith/D2N6MP5FUEJVPQ4JANR7S4MNBQ/action/replication_record"}},"created_at":"2026-07-05T10:18:01.435826+00:00","updated_at":"2026-07-05T10:18:01.435826+00:00"}