{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F4F3B6XSURWOLHT2BCN76XQLDF","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":"d6604c2f704ba787c9ffea4e9eac9895399e9f267584fd4b8b630e3364ebfd8d","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:56Z","title_canon_sha256":"187e285894a4199d28840d0ebb5566a7d28c648887b46f2ec693763c20f54a46"},"schema_version":"1.0","source":{"id":"2306.05425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05425","created_at":"2026-07-05T06:18:56Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05425v1","created_at":"2026-07-05T06:18:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05425","created_at":"2026-07-05T06:18:56Z"},{"alias_kind":"pith_short_12","alias_value":"F4F3B6XSURWO","created_at":"2026-07-05T06:18:56Z"},{"alias_kind":"pith_short_16","alias_value":"F4F3B6XSURWOLHT2","created_at":"2026-07-05T06:18:56Z"},{"alias_kind":"pith_short_8","alias_value":"F4F3B6XS","created_at":"2026-07-05T06:18:56Z"}],"graph_snapshots":[{"event_id":"sha256:0aefc814a28f855c59966095247d08067f320b06d115e439e62c4392829523ab","target":"graph","created_at":"2026-07-05T06:18:56Z","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/2306.05425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality instructions and responses are essential for the zero-shot performance of large language models on interactive natural language tasks. For interactive vision-language tasks involving intricate visual scenes, a large quantity of diverse and creative instruction-response pairs should be imperative to tune vision-language models (VLMs). Nevertheless, the current availability of vision-language instruction-response pairs in terms of quantity, diversity, and creativity remains limited, posing challenges to the generalization of interactive VLMs. Here we present MultI-Modal In-Context I","authors_text":"Bo Li, Chunyuan Li, Fanyi Pu, Jinghao Wang, Jingkang Yang, Liangyu Chen, Yuanhan Zhang, Ziwei Liu","cross_cats":["cs.AI","cs.CL","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:56Z","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05425","kind":"arxiv","version":1},"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:ab8f21fe872a05d73a7617613653290dc9b7e4a445612f03ec72080ab2f6ab77","target":"record","created_at":"2026-07-05T06:18:56Z","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":"d6604c2f704ba787c9ffea4e9eac9895399e9f267584fd4b8b630e3364ebfd8d","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:56Z","title_canon_sha256":"187e285894a4199d28840d0ebb5566a7d28c648887b46f2ec693763c20f54a46"},"schema_version":"1.0","source":{"id":"2306.05425","kind":"arxiv","version":1}},"canonical_sha256":"2f0bb0faf2a46ce59e7a089bff5e0b196e1893ead60c2a575bebd58f356770c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f0bb0faf2a46ce59e7a089bff5e0b196e1893ead60c2a575bebd58f356770c3","first_computed_at":"2026-07-05T06:18:56.920720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:56.920720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QLDVvmW06j8RlAoJwTsmeQR9Uc7TTtRLjjlvUn+CJz5Ir2vYjY+tXYEop6RL3M3+WaHidEoW/BWBZ+h37o1IAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:56.921230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab8f21fe872a05d73a7617613653290dc9b7e4a445612f03ec72080ab2f6ab77","sha256:0aefc814a28f855c59966095247d08067f320b06d115e439e62c4392829523ab"],"state_sha256":"cfe59753f6356605b49f05b9fdd457dd6f38978e31e97196b99b20bdae0a19e2"}