{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MYYHQB2SQO5K23ZCRTUDSQSE32","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":"9ef76dd4cd7ce5ca537e56dabf5e9791a8e29b8d7ba3c4c5c471108174c0319f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-20T18:59:58Z","title_canon_sha256":"325310fdf6c424f7e5b2ffd38763da71ab1f79d1ff7ef35d281a8941e42892e0"},"schema_version":"1.0","source":{"id":"2312.13286","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.13286","created_at":"2026-07-05T08:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2312.13286v2","created_at":"2026-07-05T08:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13286","created_at":"2026-07-05T08:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"MYYHQB2SQO5K","created_at":"2026-07-05T08:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"MYYHQB2SQO5K23ZC","created_at":"2026-07-05T08:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"MYYHQB2S","created_at":"2026-07-05T08:16:45Z"}],"graph_snapshots":[{"event_id":"sha256:63335a93b29dce47aa20125507bf2058d96e0c2b13341d334118a5db9af957ba","target":"graph","created_at":"2026-07-05T08:16:45Z","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/2312.13286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The human ability to easily solve multimodal tasks in context (i.e., with only a few demonstrations or simple instructions), is what current multimodal systems have largely struggled to imitate. In this work, we demonstrate that the task-agnostic in-context learning capabilities of large multimodal models can be significantly enhanced by effective scaling-up. We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences with a unified autoregressive objective. Emu2 exhibits strong multimodal in-context learning abilities, even emerging","authors_text":"Fan Zhang, Jingjing Liu, Qiying Yu, Quan Sun, Tiejun Huang, Xiaosong Zhang, Xinlong Wang, Yongming Rao, Yueze Wang, Yufeng Cui, Zhengxiong Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-20T18:59:58Z","title":"Generative Multimodal Models are In-Context Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13286","kind":"arxiv","version":2},"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:d2d00867a03575ab74893f7d7e27f1dad921f693511aea88667f7071ebc479ff","target":"record","created_at":"2026-07-05T08:16:45Z","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":"9ef76dd4cd7ce5ca537e56dabf5e9791a8e29b8d7ba3c4c5c471108174c0319f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-20T18:59:58Z","title_canon_sha256":"325310fdf6c424f7e5b2ffd38763da71ab1f79d1ff7ef35d281a8941e42892e0"},"schema_version":"1.0","source":{"id":"2312.13286","kind":"arxiv","version":2}},"canonical_sha256":"663078075283baad6f228ce8394244de84a207c850df7eb2320e04913eed36c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"663078075283baad6f228ce8394244de84a207c850df7eb2320e04913eed36c1","first_computed_at":"2026-07-05T08:16:45.632822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:45.632822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LeC+kE3fzXOdFYjGDFAyZNg+yO1jjjQYWRvVWIu5dQCHxGKphL/GBiJy/ChfNWFvDFnyzlS9TWMzIgYGBNGMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:45.633336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.13286","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2d00867a03575ab74893f7d7e27f1dad921f693511aea88667f7071ebc479ff","sha256:63335a93b29dce47aa20125507bf2058d96e0c2b13341d334118a5db9af957ba"],"state_sha256":"d8cdcc60a2830d2794b711914149153baf118dadcc1b5097234afb252bea72d9"}