{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LSNNIBDSECYZPV4JWPEPMMVSXG","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":"f0c4a8f7aefa492e28142e97dd9bbc5d056aa4a0530a0e1514ac04a207e69ba9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T21:55:56Z","title_canon_sha256":"249701a55ee6cc1b883050b46b91158b00c78937f73c5e37c1c5718a2a5fbc1d"},"schema_version":"1.0","source":{"id":"2501.04155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04155","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04155v1","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04155","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"pith_short_12","alias_value":"LSNNIBDSECYZ","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"pith_short_16","alias_value":"LSNNIBDSECYZPV4J","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"pith_short_8","alias_value":"LSNNIBDS","created_at":"2026-07-05T09:58:30Z"}],"graph_snapshots":[{"event_id":"sha256:51316511f821684e1cf197a0f722909f6ee8e65069881ca9752a8e90c2148a8e","target":"graph","created_at":"2026-07-05T09:58:30Z","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/2501.04155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are highly effective but often underperform on specialized tasks; for example, Llava-1.5 struggles with chart and diagram understanding due to scarce task-specific training data. Existing training data, sourced from general-purpose datasets, fails to capture the nuanced details needed for these tasks. We introduce MM-Gen, a scalable method that generates task-specific, high-quality synthetic text for candidate images by leveraging stronger models. MM-Gen employs a three-stage targeted process: partitioning data into subgroups, generating targeted text based on tas","authors_text":"Baharan Mirzasoleiman, Besmira Nushi, Neel Joshi, Siddharth Joshi, Varun Chandrasekaran, Vibhav Vineet, Vidhisha Balachandran","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T21:55:56Z","title":"MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04155","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":"sha256:2b044b55d3f7d5de20c363418c8fac45d58e2319189953ce073cbf35bf03eff8","target":"record","created_at":"2026-07-05T09:58:30Z","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":"f0c4a8f7aefa492e28142e97dd9bbc5d056aa4a0530a0e1514ac04a207e69ba9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T21:55:56Z","title_canon_sha256":"249701a55ee6cc1b883050b46b91158b00c78937f73c5e37c1c5718a2a5fbc1d"},"schema_version":"1.0","source":{"id":"2501.04155","kind":"arxiv","version":1}},"canonical_sha256":"5c9ad4047220b197d789b3c8f632b2b9b13bda066f2f078c324d9e4c8a7b0709","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c9ad4047220b197d789b3c8f632b2b9b13bda066f2f078c324d9e4c8a7b0709","first_computed_at":"2026-07-05T09:58:30.922711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:30.922711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rhc/WJIDvt7Bo03wZnh4oVS24E7PuVs08z0p9H7RbzHAh79DSxM4YLrffu15u3hTEmY1q1sMgWoQdQ7V1ZNXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:30.923230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b044b55d3f7d5de20c363418c8fac45d58e2319189953ce073cbf35bf03eff8","sha256:51316511f821684e1cf197a0f722909f6ee8e65069881ca9752a8e90c2148a8e"],"state_sha256":"ed90d9c8de816f99798cec4b92f5416ead8c5d1f95310643d4b8a27a5e8702c4"}