{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PYHNDJ2ISBGS26ABGGTFKSGHKT","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":"350e410ff467c07b9c0e85cf2d3f21ff6e388ca3e2ecf54b6124d6689599dd71","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-24T01:40:24Z","title_canon_sha256":"dccab5b6880b7e7dd71f10278e0bd2ecfb1629d884f2574ccf1dc304aa2ec845"},"schema_version":"1.0","source":{"id":"2409.15657","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15657","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15657v4","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15657","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"PYHNDJ2ISBGS","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"PYHNDJ2ISBGS26AB","created_at":"2026-07-05T09:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"PYHNDJ2I","created_at":"2026-07-05T09:28:13Z"}],"graph_snapshots":[{"event_id":"sha256:9b49cd4cd5be87746d3704e1cfef492884c5ef48310bc31e2abc0887f9b9d5e7","target":"graph","created_at":"2026-07-05T09:28:13Z","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/2409.15657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across various modalities. Instruction tuning has emerged as an effective strategy for achieving zero-shot generalization by finetuning pretrained models on diverse multimodal tasks. As the scale of MLLMs continues to grow, parameter-efficient finetuning becomes increasingly critical. However, most existing parameter-efficient approaches focus only on single modalities and often overlook th","authors_text":"Cheng Han, Dongfang Liu, Fuli Feng, James Chenhao Liang, Jiahao Liu, Junhan Zhao, Lifu Huang, Qifan Wang, Shaoliang Nie, Taowen Wang, Yiming Cui, Yiyang Liu, Yuning Mao, Zenglin Xu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-24T01:40:24Z","title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15657","kind":"arxiv","version":4},"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":"sha256:039bf985b1eb851798bbbf489e776e7ca2f31ff55cc9d40f981d34a0ad8bc4a3","target":"record","created_at":"2026-07-05T09:28:13Z","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":"350e410ff467c07b9c0e85cf2d3f21ff6e388ca3e2ecf54b6124d6689599dd71","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-24T01:40:24Z","title_canon_sha256":"dccab5b6880b7e7dd71f10278e0bd2ecfb1629d884f2574ccf1dc304aa2ec845"},"schema_version":"1.0","source":{"id":"2409.15657","kind":"arxiv","version":4}},"canonical_sha256":"7e0ed1a748904d2d780131a65548c754e174146712f899e8ea34b27ad130407b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e0ed1a748904d2d780131a65548c754e174146712f899e8ea34b27ad130407b","first_computed_at":"2026-07-05T09:28:13.793312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:13.793312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"78iZAgHVh5oHLoKP723gTje5IwdHsCFy56azYrmW+UhsoRYYWma/ZvEeWCh/9xEUAQUflxWVBpu0quQCXTfjCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:13.793773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15657","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:039bf985b1eb851798bbbf489e776e7ca2f31ff55cc9d40f981d34a0ad8bc4a3","sha256:9b49cd4cd5be87746d3704e1cfef492884c5ef48310bc31e2abc0887f9b9d5e7"],"state_sha256":"54719a6a13769e675f1360f1a1996dd54c66c0832516a7dfde620747691b3a89"}