{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P5UCNRH4LFOLBZAID57O6O2P5K","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":"797e152804b00290a0f3b82f768e1965b6583290fc2eb2dd92b47b874867644d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T17:50:43Z","title_canon_sha256":"a25fa53aa2ddc09614bbd90992a929ab0fbd32d335e4ad3d3f5eb445a933576a"},"schema_version":"1.0","source":{"id":"2501.12327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12327","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12327v1","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12327","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"P5UCNRH4LFOL","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"P5UCNRH4LFOLBZAI","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"P5UCNRH4","created_at":"2026-07-05T10:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:e9e79e2e5e7d68cd7dcfd4b0b6081eadc23767dbaf3ac4d580774f91050bcfd8","target":"graph","created_at":"2026-07-05T10:03:34Z","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/2501.12327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VARGPT, a novel multimodal large language model (MLLM) that unifies visual understanding and generation within a single autoregressive framework. VARGPT employs a next-token prediction paradigm for visual understanding and a next-scale prediction paradigm for visual autoregressive generation. VARGPT innovatively extends the LLaVA architecture, achieving efficient scale-wise autoregressive visual generation within MLLMs while seamlessly accommodating mixed-modal input and output within a single model framework. Our VARGPT undergoes a three-stage unified training process on specially ","authors_text":"Jinghan Ru, Liming Liang, Xianwei Zhuang, Yuexian Zou, Yufan Deng, Yuguo Yin, Yuxin Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T17:50:43Z","title":"VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12327","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:ff7229754bc03cf31aef24879e69954733a12c949d8da3e6782966cf017b6122","target":"record","created_at":"2026-07-05T10:03:34Z","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":"797e152804b00290a0f3b82f768e1965b6583290fc2eb2dd92b47b874867644d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T17:50:43Z","title_canon_sha256":"a25fa53aa2ddc09614bbd90992a929ab0fbd32d335e4ad3d3f5eb445a933576a"},"schema_version":"1.0","source":{"id":"2501.12327","kind":"arxiv","version":1}},"canonical_sha256":"7f6826c4fc595cb0e4081f7eef3b4fea84c3ec7021f1840b90bdfa1c3f4b4bd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f6826c4fc595cb0e4081f7eef3b4fea84c3ec7021f1840b90bdfa1c3f4b4bd7","first_computed_at":"2026-07-05T10:03:34.651624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:34.651624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0gFMWFkOxN44YthjEOC2zO8urdhIS6HqiMHbpW1rphUWN7/TIH8IPfyMkuFE9+KIiiK5jotdZSg/VqKg8nKWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:34.652034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff7229754bc03cf31aef24879e69954733a12c949d8da3e6782966cf017b6122","sha256:e9e79e2e5e7d68cd7dcfd4b0b6081eadc23767dbaf3ac4d580774f91050bcfd8"],"state_sha256":"59293b3c9c0c53218d44db4e368daf802350c556c368e75c41cc2a807b27e48e"}