{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ERGJH2YZ7IBASGUFMEYKH5T2LQ","short_pith_number":"pith:ERGJH2YZ","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"},"canonical_sha256":"244c93eb19fa02091a856130a3f67a5c380ecf203acda7f86a30597a1c9886f6","source":{"kind":"arxiv","id":"2409.20424","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.20424","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2409.20424v1","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20424","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"ERGJH2YZ7IBA","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"ERGJH2YZ7IBASGUF","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"ERGJH2YZ","created_at":"2026-07-05T09:13:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ERGJH2YZ7IBASGUFMEYKH5T2LQ","target":"record","payload":{"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"},"canonical_sha256":"244c93eb19fa02091a856130a3f67a5c380ecf203acda7f86a30597a1c9886f6","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"},"source_kind":"arxiv","source_id":"2409.20424","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W1WsIIjop5nosJekPPXsZQR/2aT/m5GhxRwAnSPRot7876qxRWkXJHXjbjBvGm2aO96HkpDNOiftE9OHtv3MBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:15:08.070137Z"},"content_sha256":"b9ac886d666cc6444609f5a8845545249b2b35e4ba68cea7895096dc050c02da","schema_version":"1.0","event_id":"sha256:b9ac886d666cc6444609f5a8845545249b2b35e4ba68cea7895096dc050c02da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ERGJH2YZ7IBASGUFMEYKH5T2LQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EThLGiY5GOi6CCmMqnYQIx9Ps0hCOnTOK87Fykiad+JikC4WW1mTC6u659nVZCSVUooyphIItpdJ1Z465qhdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:15:08.071001Z"},"content_sha256":"975ddfaf20a9bfc64d01200a79a0a20155099cf5ded3e00ad2f8e6f7fa3844e4","schema_version":"1.0","event_id":"sha256:975ddfaf20a9bfc64d01200a79a0a20155099cf5ded3e00ad2f8e6f7fa3844e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/bundle.json","state_url":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T09:15:08Z","links":{"resolver":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ","bundle":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/bundle.json","state":"https://pith.science/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ERGJH2YZ7IBASGUFMEYKH5T2LQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ERGJH2YZ7IBASGUFMEYKH5T2LQ","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":"1ebaecc7247a2b3e03158c6a496478f9e721092a0fec2e19c47742346f0d1d17","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T15:49:54Z","title_canon_sha256":"c862f06e4027e99a8ef27e3262a4a0ea660f5dcb4d9eed71242e51bcbe9af307"},"schema_version":"1.0","source":{"id":"2409.20424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.20424","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2409.20424v1","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20424","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"ERGJH2YZ7IBA","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"ERGJH2YZ7IBASGUF","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"ERGJH2YZ","created_at":"2026-07-05T09:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:975ddfaf20a9bfc64d01200a79a0a20155099cf5ded3e00ad2f8e6f7fa3844e4","target":"graph","created_at":"2026-07-05T09:13:43Z","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/2409.20424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bohong Wu, Haiyong Jiang, Haoyuan Guo, Jiacong Wang, Jun Xiao, Xin Xiao, Xun Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T15:49:54Z","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20424","kind":"arxiv","version":1},"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:b9ac886d666cc6444609f5a8845545249b2b35e4ba68cea7895096dc050c02da","target":"record","created_at":"2026-07-05T09:13:43Z","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":"1ebaecc7247a2b3e03158c6a496478f9e721092a0fec2e19c47742346f0d1d17","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T15:49:54Z","title_canon_sha256":"c862f06e4027e99a8ef27e3262a4a0ea660f5dcb4d9eed71242e51bcbe9af307"},"schema_version":"1.0","source":{"id":"2409.20424","kind":"arxiv","version":1}},"canonical_sha256":"244c93eb19fa02091a856130a3f67a5c380ecf203acda7f86a30597a1c9886f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"244c93eb19fa02091a856130a3f67a5c380ecf203acda7f86a30597a1c9886f6","first_computed_at":"2026-07-05T09:13:43.329636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:43.329636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ev8V/uCgddsFbnJA4dxEcEvGJ3rorm1rz5J/a+PQky2e+GBOPTNAAI8UPu+gZ0eJIiMLS2FcYxAGTmiFss1ZDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:43.330088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.20424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9ac886d666cc6444609f5a8845545249b2b35e4ba68cea7895096dc050c02da","sha256:975ddfaf20a9bfc64d01200a79a0a20155099cf5ded3e00ad2f8e6f7fa3844e4"],"state_sha256":"850c362fbad09db3659088e11638f620db627e669dd16f462cdb94eb4e4d6338"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1m9VtQBj0bRjnzOAxYRq2Lni3M1HX8ha8l+zij3mNoqAMg4kXtgWm5uJ3QG5gPuSK+B48idzkN6xxwMjQJuqAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:15:08.078486Z","bundle_sha256":"8948e78545289dc2137767ff555e7eec729220906e60c3914c93e0a10d0a2554"}}