{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TERYH6HSUZ2WJITJX6OBP6GO4Q","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":"862a48c92e8df268aae203b63629b2ed30437254092fdbcc640102e8fce0a25a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:21:25Z","title_canon_sha256":"ca606d31897dd05160dd362073360d4ccb610f4dc31695fef971fd19083531cf"},"schema_version":"1.0","source":{"id":"2311.18775","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18775","created_at":"2026-07-05T07:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18775v1","created_at":"2026-07-05T07:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18775","created_at":"2026-07-05T07:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"TERYH6HSUZ2W","created_at":"2026-07-05T07:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"TERYH6HSUZ2WJITJ","created_at":"2026-07-05T07:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"TERYH6HS","created_at":"2026-07-05T07:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:a6e31cf826db37739948d5e1f7a9b73f4d51761cd86e52dd5c123c807ce01a13","target":"graph","created_at":"2026-07-05T07:18:46Z","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/2311.18775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CoDi-2, a versatile and interactive Multimodal Large Language Model (MLLM) that can follow complex multimodal interleaved instructions, conduct in-context learning (ICL), reason, chat, edit, etc., in an any-to-any input-output modality paradigm. By aligning modalities with language for both encoding and generation, CoDi-2 empowers Large Language Models (LLMs) to not only understand complex modality-interleaved instructions and in-context examples, but also autoregressively generate grounded and coherent multimodal outputs in the continuous feature space. To train CoDi-2, we build a ","authors_text":"Chenguang Zhu, Mahmoud Khademi, Mohit Bansal, Yang Liu, Zineng Tang, Ziyi Yang","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:21:25Z","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18775","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":"sha256:1f00556beb2742eac4fee5031f8ea7cc2e463a34b7f751cbf720efa4ebfbba5b","target":"record","created_at":"2026-07-05T07:18:46Z","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":"862a48c92e8df268aae203b63629b2ed30437254092fdbcc640102e8fce0a25a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:21:25Z","title_canon_sha256":"ca606d31897dd05160dd362073360d4ccb610f4dc31695fef971fd19083531cf"},"schema_version":"1.0","source":{"id":"2311.18775","kind":"arxiv","version":1}},"canonical_sha256":"992383f8f2a67564a269bf9c17f8cee40048ef036857f904feed8232fc884a95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"992383f8f2a67564a269bf9c17f8cee40048ef036857f904feed8232fc884a95","first_computed_at":"2026-07-05T07:18:46.481990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:46.481990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PiiPi0/9hPGr89oWilgJZSzQRox+7Bag5cajORGeEdbPpd2ChybUOObQaQpAY7sRQKsN1o0VY/zY0eyIq6eRBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:46.482453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.18775","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f00556beb2742eac4fee5031f8ea7cc2e463a34b7f751cbf720efa4ebfbba5b","sha256:a6e31cf826db37739948d5e1f7a9b73f4d51761cd86e52dd5c123c807ce01a13"],"state_sha256":"d48372ad89942a6205dd2f76e5615d62eb9ef14011866f78f37c78cf16f01fc7"}