{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ERGJH2YZ7IBASGUFMEYKH5T2LQ","short_pith_number":"pith:ERGJH2YZ","schema_version":"1.0","canonical_sha256":"244c93eb19fa02091a856130a3f67a5c380ecf203acda7f86a30597a1c9886f6","source":{"kind":"arxiv","id":"2409.20424","version":1},"attestation_state":"computed","paper":{"title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bohong Wu, Haiyong Jiang, Haoyuan Guo, Jiacong Wang, Jun Xiao, Xin Xiao, Xun Zhou","submitted_at":"2024-09-30T15:49:54Z","abstract_excerpt":"Recent advances in Vision-Language Models (VLMs) and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation. The conventional norm in VLM data construction uses a mixture of specialists in caption and OCR, or stronger VLM APIs and expensive human annotation. In this paper, we present World to Code (W2C), a meticulously curated multi-modal data construction pipeline that organizes the final generation output into a Python code format. The pipeline leverages the VLM itself to extract cross-modal information via different prompts"},"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":"2409.20424","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T15:49:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c862f06e4027e99a8ef27e3262a4a0ea660f5dcb4d9eed71242e51bcbe9af307","abstract_canon_sha256":"1ebaecc7247a2b3e03158c6a496478f9e721092a0fec2e19c47742346f0d1d17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:43.330088Z","signature_b64":"Ev8V/uCgddsFbnJA4dxEcEvGJ3rorm1rz5J/a+PQky2e+GBOPTNAAI8UPu+gZ0eJIiMLS2FcYxAGTmiFss1ZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"244c93eb19fa02091a856130a3f67a5c380ecf203acda7f86a30597a1c9886f6","last_reissued_at":"2026-07-05T09:13:43.329636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:43.329636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bohong Wu, Haiyong Jiang, Haoyuan Guo, Jiacong Wang, Jun Xiao, Xin Xiao, Xun Zhou","submitted_at":"2024-09-30T15:49:54Z","abstract_excerpt":"Recent advances in Vision-Language Models (VLMs) and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation. The conventional norm in VLM data construction uses a mixture of specialists in caption and OCR, or stronger VLM APIs and expensive human annotation. In this paper, we present World to Code (W2C), a meticulously curated multi-modal data construction pipeline that organizes the final generation output into a Python code format. The pipeline leverages the VLM itself to extract cross-modal information via different prompts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20424","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/2409.20424/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":"2409.20424","created_at":"2026-07-05T09:13:43.329692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20424v1","created_at":"2026-07-05T09:13:43.329692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20424","created_at":"2026-07-05T09:13:43.329692+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERGJH2YZ7IBA","created_at":"2026-07-05T09:13:43.329692+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERGJH2YZ7IBASGUF","created_at":"2026-07-05T09:13:43.329692+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERGJH2YZ","created_at":"2026-07-05T09:13:43.329692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03885","citing_title":"MuRA: Multi-Rank Adaptation for Efficient and Effective Test-Time Vision-Language Generalization","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ","json":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ.json","graph_json":"https://pith.science/api/pith-number/ERGJH2YZ7IBASGUFMEYKH5T2LQ/graph.json","events_json":"https://pith.science/api/pith-number/ERGJH2YZ7IBASGUFMEYKH5T2LQ/events.json","paper":"https://pith.science/paper/ERGJH2YZ"},"agent_actions":{"view_html":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ","download_json":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ.json","view_paper":"https://pith.science/paper/ERGJH2YZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20424&json=true","fetch_graph":"https://pith.science/api/pith-number/ERGJH2YZ7IBASGUFMEYKH5T2LQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ERGJH2YZ7IBASGUFMEYKH5T2LQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/action/storage_attestation","attest_author":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/action/author_attestation","sign_citation":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/action/citation_signature","submit_replication":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/action/replication_record"}},"created_at":"2026-07-05T09:13:43.329692+00:00","updated_at":"2026-07-05T09:13:43.329692+00:00"}