{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DC5PCRAQNNJPU77QFI5SA5CMYS","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":"a71924a8448da555befefc487181d1411bffdcc71427aab32024543fd5169bcf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T17:53:29Z","title_canon_sha256":"aaf5b0ec3f9803b84b74bd1928e2bff6f441e2842b859fb2cc47bd7b9fad0ba5"},"schema_version":"1.0","source":{"id":"2309.14327","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.14327","created_at":"2026-07-05T07:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2309.14327v3","created_at":"2026-07-05T07:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14327","created_at":"2026-07-05T07:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"DC5PCRAQNNJP","created_at":"2026-07-05T07:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"DC5PCRAQNNJPU77Q","created_at":"2026-07-05T07:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"DC5PCRAQ","created_at":"2026-07-05T07:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:4555023522e60b0a82c422e6b6ea210ce82049223c1d69e47848a5955adc8bcf","target":"graph","created_at":"2026-07-05T07:17:54Z","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/2309.14327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most of the existing multi-modal models, hindered by their incapacity to adeptly manage interleaved image-and-text inputs in multi-image, multi-round dialogues, face substantial constraints in resource allocation for training and data accessibility, impacting their adaptability and scalability across varied interaction realms. To address this, we present the DeepSpeed-VisualChat framework, designed to optimize Large Language Models (LLMs) by incorporating multi-modal capabilities, with a focus on enhancing the proficiency of Large Vision and Language Models in handling interleaved inputs. Our ","authors_text":"Ammar Ahmad Awan, Conglong Li, Heyang Qin, Minjia Zhang, Olatunji Ruwase, Samyam Rajbhandari, Xiaoxia Wu, Yuxiong He, Zhewei Yao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T17:53:29Z","title":"DeepSpeed-VisualChat: Multi-Round Multi-Image Interleave Chat via Multi-Modal Causal Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14327","kind":"arxiv","version":3},"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:f0ddd005b5738f8447edb60d10fd41bd4307aa7520cfb92b6ac6aba6bdfa7263","target":"record","created_at":"2026-07-05T07:17:54Z","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":"a71924a8448da555befefc487181d1411bffdcc71427aab32024543fd5169bcf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T17:53:29Z","title_canon_sha256":"aaf5b0ec3f9803b84b74bd1928e2bff6f441e2842b859fb2cc47bd7b9fad0ba5"},"schema_version":"1.0","source":{"id":"2309.14327","kind":"arxiv","version":3}},"canonical_sha256":"18baf144106b52fa7ff02a3b20744cc4b3d57f0d3c023df93fb29df635fab324","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18baf144106b52fa7ff02a3b20744cc4b3d57f0d3c023df93fb29df635fab324","first_computed_at":"2026-07-05T07:17:54.944834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:54.944834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nGFHUaGRTJM9CitFWlyzBw2iC3kenxmY1MlkwVQGY67merbeJaTi4KWE4BQDjR3sWCjf601IhTG8x5hwRqdTCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:54.945323Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.14327","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0ddd005b5738f8447edb60d10fd41bd4307aa7520cfb92b6ac6aba6bdfa7263","sha256:4555023522e60b0a82c422e6b6ea210ce82049223c1d69e47848a5955adc8bcf"],"state_sha256":"61a9796b06627a898f04ea3ddc28171ac6164d43ed0f52d242f7db52e162934c"}