{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EMAQ37RZDY7KMOPGRJPX7UQ2CT","short_pith_number":"pith:EMAQ37RZ","schema_version":"1.0","canonical_sha256":"23010dfe391e3ea639e68a5f7fd21a14f18a63b0230127f979dcb6fd1e0ef128","source":{"kind":"arxiv","id":"2407.08583","version":2},"attestation_state":"computed","paper":{"title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Bolin Ding, Daoyuan Chen, Liuyi Yao, Shuiguang Deng, Wenhao Zhang, Yaliang Li, Yilun Huang, Zhen Qin","submitted_at":"2024-07-11T15:08:11Z","abstract_excerpt":"The rapid development of large language models (LLMs) has been witnessed in recent years. Based on the powerful LLMs, multi-modal LLMs (MLLMs) extend the modality from text to a broader spectrum of domains, attracting widespread attention due to the broader range of application scenarios. As LLMs and MLLMs rely on vast amounts of model parameters and data to achieve emergent capabilities, the importance of data is receiving increasingly widespread attention and recognition. Tracing and analyzing recent data-oriented works for MLLMs, we find that the development of models and data is not two se"},"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":"2407.08583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T15:08:11Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"555c3529662c0c97ef958d74bdb017b3fae8bd035c8c5096d355a53b85ee2287","abstract_canon_sha256":"5783ed61f25ce1389048a762694f1d56e3a56f6603cf306aca7386bf4b896c3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:54.666946Z","signature_b64":"zmIp33v45pL9pd7AaaQX/okJvEzwhqK6ofoODQmeeWCm5VixSVP4lF2Pc1TIZKsINhyGvzLNlxHU5NvNfydUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23010dfe391e3ea639e68a5f7fd21a14f18a63b0230127f979dcb6fd1e0ef128","last_reissued_at":"2026-07-05T08:51:54.666408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:54.666408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Bolin Ding, Daoyuan Chen, Liuyi Yao, Shuiguang Deng, Wenhao Zhang, Yaliang Li, Yilun Huang, Zhen Qin","submitted_at":"2024-07-11T15:08:11Z","abstract_excerpt":"The rapid development of large language models (LLMs) has been witnessed in recent years. Based on the powerful LLMs, multi-modal LLMs (MLLMs) extend the modality from text to a broader spectrum of domains, attracting widespread attention due to the broader range of application scenarios. As LLMs and MLLMs rely on vast amounts of model parameters and data to achieve emergent capabilities, the importance of data is receiving increasingly widespread attention and recognition. Tracing and analyzing recent data-oriented works for MLLMs, we find that the development of models and data is not two se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08583","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/2407.08583/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":"2407.08583","created_at":"2026-07-05T08:51:54.666470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08583v2","created_at":"2026-07-05T08:51:54.666470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08583","created_at":"2026-07-05T08:51:54.666470+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMAQ37RZDY7K","created_at":"2026-07-05T08:51:54.666470+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMAQ37RZDY7KMOPG","created_at":"2026-07-05T08:51:54.666470+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMAQ37RZ","created_at":"2026-07-05T08:51:54.666470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.17574","citing_title":"HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMAQ37RZDY7KMOPGRJPX7UQ2CT","json":"https://pith.science/pith/EMAQ37RZDY7KMOPGRJPX7UQ2CT.json","graph_json":"https://pith.science/api/pith-number/EMAQ37RZDY7KMOPGRJPX7UQ2CT/graph.json","events_json":"https://pith.science/api/pith-number/EMAQ37RZDY7KMOPGRJPX7UQ2CT/events.json","paper":"https://pith.science/paper/EMAQ37RZ"},"agent_actions":{"view_html":"https://pith.science/pith/EMAQ37RZDY7KMOPGRJPX7UQ2CT","download_json":"https://pith.science/pith/EMAQ37RZDY7KMOPGRJPX7UQ2CT.json","view_paper":"https://pith.science/paper/EMAQ37RZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08583&json=true","fetch_graph":"https://pith.science/api/pith-number/EMAQ37RZDY7KMOPGRJPX7UQ2CT/graph.json","fetch_events":"https://pith.science/api/pith-number/EMAQ37RZDY7KMOPGRJPX7UQ2CT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMAQ37RZDY7KMOPGRJPX7UQ2CT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMAQ37RZDY7KMOPGRJPX7UQ2CT/action/storage_attestation","attest_author":"https://pith.science/pith/EMAQ37RZDY7KMOPGRJPX7UQ2CT/action/author_attestation","sign_citation":"https://pith.science/pith/EMAQ37RZDY7KMOPGRJPX7UQ2CT/action/citation_signature","submit_replication":"https://pith.science/pith/EMAQ37RZDY7KMOPGRJPX7UQ2CT/action/replication_record"}},"created_at":"2026-07-05T08:51:54.666470+00:00","updated_at":"2026-07-05T08:51:54.666470+00:00"}