{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QBQRWSWITBVP2GIRBFKOBBSQ2T","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":"6b0830ace6ad5dc4280a26bad0c4baa48c7fbb36f964b04d725903159820ebdc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-19T15:27:25Z","title_canon_sha256":"809cc0d014893993fbcd75a1b7e3688fccb8a62aba391cd38025a0d8fc573c04"},"schema_version":"1.0","source":{"id":"2408.10086","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10086","created_at":"2026-07-05T08:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10086v1","created_at":"2026-07-05T08:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10086","created_at":"2026-07-05T08:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"QBQRWSWITBVP","created_at":"2026-07-05T08:56:51Z"},{"alias_kind":"pith_short_16","alias_value":"QBQRWSWITBVP2GIR","created_at":"2026-07-05T08:56:51Z"},{"alias_kind":"pith_short_8","alias_value":"QBQRWSWI","created_at":"2026-07-05T08:56:51Z"}],"graph_snapshots":[{"event_id":"sha256:898766ee00b516141bf81c1ce2e2fbac68c6da4b39da352f3033f358fa2d6770","target":"graph","created_at":"2026-07-05T08:56:51Z","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/2408.10086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Multimodal Language Models (MLMs), the cost of manually annotating high-quality image-text pair data for fine-tuning and alignment is extremely high. While existing multimodal data augmentation frameworks propose ways to augment image-text pairs, they either suffer from semantic inconsistency between texts and images, or generate unrealistic images, causing knowledge gap with real world examples. To address these issues, we propose Attribute-based Multimodal Data Augmentation (ARMADA), a novel multimodal data augmentation method via knowledge-guided manipulation of visual attributes of the ","authors_text":"Heng Ji, Jeonghwan Kim, Kuan-Hao Huang, Nanyun Peng, Te-Lin Wu, Xiaomeng Jin, Yu Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-19T15:27:25Z","title":"ARMADA: Attribute-Based Multimodal Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10086","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":"sha256:96c63e0d243c69c854cf7ffdfe13e6f66c31169781e46e87a8a1f2a52e71f7e1","target":"record","created_at":"2026-07-05T08:56:51Z","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":"6b0830ace6ad5dc4280a26bad0c4baa48c7fbb36f964b04d725903159820ebdc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-19T15:27:25Z","title_canon_sha256":"809cc0d014893993fbcd75a1b7e3688fccb8a62aba391cd38025a0d8fc573c04"},"schema_version":"1.0","source":{"id":"2408.10086","kind":"arxiv","version":1}},"canonical_sha256":"80611b4ac8986afd19110954e08650d4db37e6b38816e4eaebb9ed82b5824209","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80611b4ac8986afd19110954e08650d4db37e6b38816e4eaebb9ed82b5824209","first_computed_at":"2026-07-05T08:56:51.131559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:51.131559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tfLMCV7lj9hZn7a8cN6FyX1T9GBYHGoU8v+xtPY+ZN73B14YHX7u+iUk/HfiMavrLXeBfo8+7bJz19gXWf2YDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:51.131982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10086","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96c63e0d243c69c854cf7ffdfe13e6f66c31169781e46e87a8a1f2a52e71f7e1","sha256:898766ee00b516141bf81c1ce2e2fbac68c6da4b39da352f3033f358fa2d6770"],"state_sha256":"d034cf73faf58a959095b545ea3e1aa5b31e4f5fa968f8baa114f5347955bc92"}