{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TVTN2SYNWL45527Z53A3UKXBPB","short_pith_number":"pith:TVTN2SYN","schema_version":"1.0","canonical_sha256":"9d66dd4b0db2f9deebf9eec1ba2ae1784fce3d9f104793444ffc15dfc0b01362","source":{"kind":"arxiv","id":"2312.16602","version":1},"attestation_state":"computed","paper":{"title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Qiu, Jiaxing Huang, Jingyi Zhang, Kai Jiang, Shijian Lu","submitted_at":"2023-12-27T14:54:37Z","abstract_excerpt":"Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions. To address them, Visual Instruction Tuning (VIT) has been intensively studied recently, which finetunes a large vision"},"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":"2312.16602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-27T14:54:37Z","cross_cats_sorted":[],"title_canon_sha256":"3461984ebbff57adb60e8e2d75373324b3cf121943032c2edcd2936aaa257128","abstract_canon_sha256":"de8f3369ae86b212dc6e26636bc5ee5c0780266cc4ccd7d3632b9dd8b167c2af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:19.719540Z","signature_b64":"bVkMtmoUq3Cx+nNKyZFIOqcacnYGabpDofgU7Z7RmAZ5u+nIQJ/bBVAXLCbQINXVq3PNR/eSEi2CeHJg+E0yAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d66dd4b0db2f9deebf9eec1ba2ae1784fce3d9f104793444ffc15dfc0b01362","last_reissued_at":"2026-07-05T07:28:19.718970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:19.718970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Qiu, Jiaxing Huang, Jingyi Zhang, Kai Jiang, Shijian Lu","submitted_at":"2023-12-27T14:54:37Z","abstract_excerpt":"Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions. To address them, Visual Instruction Tuning (VIT) has been intensively studied recently, which finetunes a large vision"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16602","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/2312.16602/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":"2312.16602","created_at":"2026-07-05T07:28:19.719038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16602v1","created_at":"2026-07-05T07:28:19.719038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16602","created_at":"2026-07-05T07:28:19.719038+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVTN2SYNWL45","created_at":"2026-07-05T07:28:19.719038+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVTN2SYNWL45527Z","created_at":"2026-07-05T07:28:19.719038+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVTN2SYN","created_at":"2026-07-05T07:28:19.719038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.21850","citing_title":"Visual Compositional Tuning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15687","citing_title":"ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14069","citing_title":"Towards Unconstrained Human-Object Interaction","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB","json":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB.json","graph_json":"https://pith.science/api/pith-number/TVTN2SYNWL45527Z53A3UKXBPB/graph.json","events_json":"https://pith.science/api/pith-number/TVTN2SYNWL45527Z53A3UKXBPB/events.json","paper":"https://pith.science/paper/TVTN2SYN"},"agent_actions":{"view_html":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB","download_json":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB.json","view_paper":"https://pith.science/paper/TVTN2SYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16602&json=true","fetch_graph":"https://pith.science/api/pith-number/TVTN2SYNWL45527Z53A3UKXBPB/graph.json","fetch_events":"https://pith.science/api/pith-number/TVTN2SYNWL45527Z53A3UKXBPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB/action/storage_attestation","attest_author":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB/action/author_attestation","sign_citation":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB/action/citation_signature","submit_replication":"https://pith.science/pith/TVTN2SYNWL45527Z53A3UKXBPB/action/replication_record"}},"created_at":"2026-07-05T07:28:19.719038+00:00","updated_at":"2026-07-05T07:28:19.719038+00:00"}