{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:X3GTCZB4L53UX46WZQTNM2IYXB","short_pith_number":"pith:X3GTCZB4","schema_version":"1.0","canonical_sha256":"becd31643c5f774bf3d6cc26d66918b84cfb43e7f170ecb9e386dc8860303421","source":{"kind":"arxiv","id":"2212.10773","version":3},"attestation_state":"computed","paper":{"title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lifu Huang, Ying Shen, Zhiyang Xu","submitted_at":"2022-12-21T05:17:06Z","abstract_excerpt":"Instruction tuning, a new learning paradigm that fine-tunes pre-trained language models on tasks specified through instructions, has shown promising zero-shot performance on various natural language processing tasks. However, it has yet to be explored for vision and multimodal tasks. In this work, we introduce MUL-TIINSTRUCT, the first multimodal instruction tuning benchmark dataset that consists of 62 diverse multimodal tasks in a unified seq-to-seq format covering 10 broad categories. The tasks are derived from 21 existing open-source datasets and each task is equipped with 5 expert-written "},"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":"2212.10773","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T05:17:06Z","cross_cats_sorted":[],"title_canon_sha256":"fb31fd2ab51df2e5db14eaa2da8118b4d79fe86b89f3f9f716cd283996c355d6","abstract_canon_sha256":"6cd4c1bb9dc998562803fab1164d475ea8e27d41008425fa8457c49064862e02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:17.412490Z","signature_b64":"wesVNlmjKsKHfwq/YC6fcILdpLiFyBMuXiPOf6LtB3XSEQwM6uD4gY5C26W8XBE4EKwA3VG6hnftZZ7j0iGDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"becd31643c5f774bf3d6cc26d66918b84cfb43e7f170ecb9e386dc8860303421","last_reissued_at":"2026-07-05T06:19:17.412066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:17.412066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lifu Huang, Ying Shen, Zhiyang Xu","submitted_at":"2022-12-21T05:17:06Z","abstract_excerpt":"Instruction tuning, a new learning paradigm that fine-tunes pre-trained language models on tasks specified through instructions, has shown promising zero-shot performance on various natural language processing tasks. However, it has yet to be explored for vision and multimodal tasks. In this work, we introduce MUL-TIINSTRUCT, the first multimodal instruction tuning benchmark dataset that consists of 62 diverse multimodal tasks in a unified seq-to-seq format covering 10 broad categories. The tasks are derived from 21 existing open-source datasets and each task is equipped with 5 expert-written "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10773","kind":"arxiv","version":3},"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/2212.10773/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":"2212.10773","created_at":"2026-07-05T06:19:17.412132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10773v3","created_at":"2026-07-05T06:19:17.412132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10773","created_at":"2026-07-05T06:19:17.412132+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3GTCZB4L53U","created_at":"2026-07-05T06:19:17.412132+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3GTCZB4L53UX46W","created_at":"2026-07-05T06:19:17.412132+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3GTCZB4","created_at":"2026-07-05T06:19:17.412132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2301.13688","citing_title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":280,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2305.03726","citing_title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06500","citing_title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13394","citing_title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X3GTCZB4L53UX46WZQTNM2IYXB","json":"https://pith.science/pith/X3GTCZB4L53UX46WZQTNM2IYXB.json","graph_json":"https://pith.science/api/pith-number/X3GTCZB4L53UX46WZQTNM2IYXB/graph.json","events_json":"https://pith.science/api/pith-number/X3GTCZB4L53UX46WZQTNM2IYXB/events.json","paper":"https://pith.science/paper/X3GTCZB4"},"agent_actions":{"view_html":"https://pith.science/pith/X3GTCZB4L53UX46WZQTNM2IYXB","download_json":"https://pith.science/pith/X3GTCZB4L53UX46WZQTNM2IYXB.json","view_paper":"https://pith.science/paper/X3GTCZB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10773&json=true","fetch_graph":"https://pith.science/api/pith-number/X3GTCZB4L53UX46WZQTNM2IYXB/graph.json","fetch_events":"https://pith.science/api/pith-number/X3GTCZB4L53UX46WZQTNM2IYXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3GTCZB4L53UX46WZQTNM2IYXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3GTCZB4L53UX46WZQTNM2IYXB/action/storage_attestation","attest_author":"https://pith.science/pith/X3GTCZB4L53UX46WZQTNM2IYXB/action/author_attestation","sign_citation":"https://pith.science/pith/X3GTCZB4L53UX46WZQTNM2IYXB/action/citation_signature","submit_replication":"https://pith.science/pith/X3GTCZB4L53UX46WZQTNM2IYXB/action/replication_record"}},"created_at":"2026-07-05T06:19:17.412132+00:00","updated_at":"2026-07-05T06:19:17.412132+00:00"}