{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ELNQ47OUGX735CCYVDC5E4I73O","short_pith_number":"pith:ELNQ47OU","schema_version":"1.0","canonical_sha256":"22db0e7dd435ffbe8858a8c5d2711fdb8569b1ada51bb30e59ee7ff1f7d8f843","source":{"kind":"arxiv","id":"2408.02503","version":1},"attestation_state":"computed","paper":{"title":"UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Botian Jiang, Dong Zhang, Hang Song, Pengyu Wang, Tao Wang, Wei Wang, Xu Qi, Yiqing Cai, Zhaowei Li, Zhida Huang","submitted_at":"2024-08-05T14:27:39Z","abstract_excerpt":"Significant advancements has recently been achieved in the field of multi-modal large language models (MLLMs), demonstrating their remarkable capabilities in understanding and reasoning across diverse tasks. However, these models are often trained for specific tasks and rely on task-specific input-output formats, limiting their applicability to a broader range of tasks. This raises a fundamental question: Can we develop a unified approach to represent and handle different multi-modal tasks to maximize the generalizability of MLLMs? In this paper, we propose UnifiedMLLM, a comprehensive model d"},"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":"2408.02503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T14:27:39Z","cross_cats_sorted":[],"title_canon_sha256":"fc6a589474fa13e3bdee880a554ea13331677248f49fd06af143c344d3fda8ef","abstract_canon_sha256":"57b8725c49d7bf2208ab8bb4874a00d95200663c1894f098a5036696af31b166"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:13.627196Z","signature_b64":"uVce+nZeQNP16sYkKLecYF/32FPMi9SwA1rzQA/0rgW88eoetPJjNNiZrKKrmU3v4lMLmEEbhKGJLVw42cf1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22db0e7dd435ffbe8858a8c5d2711fdb8569b1ada51bb30e59ee7ff1f7d8f843","last_reissued_at":"2026-07-05T08:52:13.626777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:13.626777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Botian Jiang, Dong Zhang, Hang Song, Pengyu Wang, Tao Wang, Wei Wang, Xu Qi, Yiqing Cai, Zhaowei Li, Zhida Huang","submitted_at":"2024-08-05T14:27:39Z","abstract_excerpt":"Significant advancements has recently been achieved in the field of multi-modal large language models (MLLMs), demonstrating their remarkable capabilities in understanding and reasoning across diverse tasks. However, these models are often trained for specific tasks and rely on task-specific input-output formats, limiting their applicability to a broader range of tasks. This raises a fundamental question: Can we develop a unified approach to represent and handle different multi-modal tasks to maximize the generalizability of MLLMs? In this paper, we propose UnifiedMLLM, a comprehensive model d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02503","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/2408.02503/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":"2408.02503","created_at":"2026-07-05T08:52:13.626829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02503v1","created_at":"2026-07-05T08:52:13.626829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02503","created_at":"2026-07-05T08:52:13.626829+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELNQ47OUGX73","created_at":"2026-07-05T08:52:13.626829+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELNQ47OUGX735CCY","created_at":"2026-07-05T08:52:13.626829+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELNQ47OU","created_at":"2026-07-05T08:52:13.626829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23762","citing_title":"Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead","ref_index":194,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELNQ47OUGX735CCYVDC5E4I73O","json":"https://pith.science/pith/ELNQ47OUGX735CCYVDC5E4I73O.json","graph_json":"https://pith.science/api/pith-number/ELNQ47OUGX735CCYVDC5E4I73O/graph.json","events_json":"https://pith.science/api/pith-number/ELNQ47OUGX735CCYVDC5E4I73O/events.json","paper":"https://pith.science/paper/ELNQ47OU"},"agent_actions":{"view_html":"https://pith.science/pith/ELNQ47OUGX735CCYVDC5E4I73O","download_json":"https://pith.science/pith/ELNQ47OUGX735CCYVDC5E4I73O.json","view_paper":"https://pith.science/paper/ELNQ47OU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02503&json=true","fetch_graph":"https://pith.science/api/pith-number/ELNQ47OUGX735CCYVDC5E4I73O/graph.json","fetch_events":"https://pith.science/api/pith-number/ELNQ47OUGX735CCYVDC5E4I73O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELNQ47OUGX735CCYVDC5E4I73O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELNQ47OUGX735CCYVDC5E4I73O/action/storage_attestation","attest_author":"https://pith.science/pith/ELNQ47OUGX735CCYVDC5E4I73O/action/author_attestation","sign_citation":"https://pith.science/pith/ELNQ47OUGX735CCYVDC5E4I73O/action/citation_signature","submit_replication":"https://pith.science/pith/ELNQ47OUGX735CCYVDC5E4I73O/action/replication_record"}},"created_at":"2026-07-05T08:52:13.626829+00:00","updated_at":"2026-07-05T08:52:13.626829+00:00"}