{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NPD6UFJ2AKI3UWWHFCQ6ESE7XK","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":"c6906c2e6d60c142b904ee8cac3c92dffcec7af526444dcad4e1fa401a4786a9","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-28T17:43:00Z","title_canon_sha256":"ab74feb25373d63b5e078395d5c6abbffe354264deabdd289fa92b2b485ee5c7"},"schema_version":"1.0","source":{"id":"2503.22655","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22655","created_at":"2026-05-28T01:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22655v2","created_at":"2026-05-28T01:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22655","created_at":"2026-05-28T01:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"NPD6UFJ2AKI3","created_at":"2026-05-28T01:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"NPD6UFJ2AKI3UWWH","created_at":"2026-05-28T01:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"NPD6UFJ2","created_at":"2026-05-28T01:04:27Z"}],"graph_snapshots":[{"event_id":"sha256:9ef97bcc952de9c955a7c41e8254f9601aa701a59c4af8ec90cc7accc8f606d2","target":"graph","created_at":"2026-05-28T01:04:27Z","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/2503.22655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training vision-language models (VLMs) typically requires large-scale, high-quality image-text pairs, but collecting or synthesizing such data is costly. In contrast, text data is abundant and inexpensive, prompting the question: can high-quality multimodal training data be synthesized purely from text? To tackle this, we propose a cross-integrated three-stage multimodal data synthesis framework, which generates two datasets: Unicorn-1.2M and Unicorn-471K-Instruction. In Stage 1: Diverse Caption Data Synthesis, we construct 1.2M semantically diverse high-quality captions by expanding sparse ca","authors_text":"Chengwei Qin, Hui Xiong, Wenjie Zhang, Xiaomin Yu, Ziyue Qiao","cross_cats":["cs.CV","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-28T17:43:00Z","title":"Text-Only Data Synthesis for Vision Language Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22655","kind":"arxiv","version":2},"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":"sha256:20717ea2b65b83d22b87cf4517576c7bd7986d6b7b546c14a0ec0ad249c426e2","target":"record","created_at":"2026-05-28T01:04:27Z","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":"c6906c2e6d60c142b904ee8cac3c92dffcec7af526444dcad4e1fa401a4786a9","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-28T17:43:00Z","title_canon_sha256":"ab74feb25373d63b5e078395d5c6abbffe354264deabdd289fa92b2b485ee5c7"},"schema_version":"1.0","source":{"id":"2503.22655","kind":"arxiv","version":2}},"canonical_sha256":"6bc7ea153a0291ba5ac728a1e2489fba90b4aa35b1ff1cbb461d0a1b92955dd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bc7ea153a0291ba5ac728a1e2489fba90b4aa35b1ff1cbb461d0a1b92955dd1","first_computed_at":"2026-05-28T01:04:27.514655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:27.514655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1jUin5C5UKTskBuXacH/q4Jq8EDpdiqKeoQ+2snngJnnAxeC50qRhyCyWgn1iln+Rd7DJhJTac76q0swnXPjAg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:27.516419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22655","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20717ea2b65b83d22b87cf4517576c7bd7986d6b7b546c14a0ec0ad249c426e2","sha256:9ef97bcc952de9c955a7c41e8254f9601aa701a59c4af8ec90cc7accc8f606d2"],"state_sha256":"833c9ebd809ce0dffdf73ddaf564639dfca451c1fb455c83d8f906f7324fa4e9"}