{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZCZWLVYMMP7ST5Y4QVKVSX2J4T","short_pith_number":"pith:ZCZWLVYM","schema_version":"1.0","canonical_sha256":"c8b365d70c63ff29f71c8555595f49e4c6828778b2789a3e9eca652984c930a9","source":{"kind":"arxiv","id":"2602.03300","version":2},"attestation_state":"computed","paper":{"title":"R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Huanjin Yao, Jiaxing Huang, Jingyi Zhang, Shunyu Liu, Tianyi Lin, Xiang Lan","submitted_at":"2026-02-03T09:26:32Z","abstract_excerpt":"In this work, we aim to develop effective data synthesis techniques that autonomously synthesize multimodal training data for enhancing MLLMs in solving complex real-world tasks. To this end, we propose Collective Adversarial Data Synthesis (CADS), a novel and general approach to synthesize high-quality, diverse and challenging multimodal data for MLLMs. The core idea of CADS is to leverage collective intelligence to ensure high-quality and diverse generation, while exploring adversarial learning to synthesize challenging samples for effectively driving model improvement. Specifically, CADS op"},"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":"2602.03300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T09:26:32Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"0ed8b9e8f5ae52812a4e8f17b9f4b7bb32e32ae9fc667a545b4d9b0673abae29","abstract_canon_sha256":"f3918cef2b3c13a282fd88cd5877a05dc3432daf55b28dd6942ea84b6876659d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:54.362808Z","signature_b64":"Mg8SUgwy5dy23VLCbcX2ejMYEuFC6mxFztjlE36j4lGa0zNAa1H5VRjze1FR+OLIRRaS7gDCQlY1AdSaMl61Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8b365d70c63ff29f71c8555595f49e4c6828778b2789a3e9eca652984c930a9","last_reissued_at":"2026-06-19T16:09:54.362390Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:54.362390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Huanjin Yao, Jiaxing Huang, Jingyi Zhang, Shunyu Liu, Tianyi Lin, Xiang Lan","submitted_at":"2026-02-03T09:26:32Z","abstract_excerpt":"In this work, we aim to develop effective data synthesis techniques that autonomously synthesize multimodal training data for enhancing MLLMs in solving complex real-world tasks. To this end, we propose Collective Adversarial Data Synthesis (CADS), a novel and general approach to synthesize high-quality, diverse and challenging multimodal data for MLLMs. The core idea of CADS is to leverage collective intelligence to ensure high-quality and diverse generation, while exploring adversarial learning to synthesize challenging samples for effectively driving model improvement. Specifically, CADS op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03300","kind":"arxiv","version":2},"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/2602.03300/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":"2602.03300","created_at":"2026-06-19T16:09:54.362446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.03300v2","created_at":"2026-06-19T16:09:54.362446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03300","created_at":"2026-06-19T16:09:54.362446+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCZWLVYMMP7S","created_at":"2026-06-19T16:09:54.362446+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCZWLVYMMP7ST5Y4","created_at":"2026-06-19T16:09:54.362446+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCZWLVYM","created_at":"2026-06-19T16:09:54.362446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZCZWLVYMMP7ST5Y4QVKVSX2J4T","json":"https://pith.science/pith/ZCZWLVYMMP7ST5Y4QVKVSX2J4T.json","graph_json":"https://pith.science/api/pith-number/ZCZWLVYMMP7ST5Y4QVKVSX2J4T/graph.json","events_json":"https://pith.science/api/pith-number/ZCZWLVYMMP7ST5Y4QVKVSX2J4T/events.json","paper":"https://pith.science/paper/ZCZWLVYM"},"agent_actions":{"view_html":"https://pith.science/pith/ZCZWLVYMMP7ST5Y4QVKVSX2J4T","download_json":"https://pith.science/pith/ZCZWLVYMMP7ST5Y4QVKVSX2J4T.json","view_paper":"https://pith.science/paper/ZCZWLVYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.03300&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCZWLVYMMP7ST5Y4QVKVSX2J4T/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCZWLVYMMP7ST5Y4QVKVSX2J4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCZWLVYMMP7ST5Y4QVKVSX2J4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCZWLVYMMP7ST5Y4QVKVSX2J4T/action/storage_attestation","attest_author":"https://pith.science/pith/ZCZWLVYMMP7ST5Y4QVKVSX2J4T/action/author_attestation","sign_citation":"https://pith.science/pith/ZCZWLVYMMP7ST5Y4QVKVSX2J4T/action/citation_signature","submit_replication":"https://pith.science/pith/ZCZWLVYMMP7ST5Y4QVKVSX2J4T/action/replication_record"}},"created_at":"2026-06-19T16:09:54.362446+00:00","updated_at":"2026-06-19T16:09:54.362446+00:00"}