{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L575ERTKOBJAZ25BPUKFBYVVQG","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":"458e933f547f22d56c3c5954b2d3950866b96b2877ac04de571a55162f3a463a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T16:12:50Z","title_canon_sha256":"397e5cf7550ccda652b003747657d81812138abed249a389a7fac6793033d572"},"schema_version":"1.0","source":{"id":"2503.07493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07493","created_at":"2026-07-05T10:27:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07493v1","created_at":"2026-07-05T10:27:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07493","created_at":"2026-07-05T10:27:57Z"},{"alias_kind":"pith_short_12","alias_value":"L575ERTKOBJA","created_at":"2026-07-05T10:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"L575ERTKOBJAZ25B","created_at":"2026-07-05T10:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"L575ERTK","created_at":"2026-07-05T10:27:57Z"}],"graph_snapshots":[{"event_id":"sha256:1b9f5d7a0306b0eac946ceb609a5c76bf5fa29da789538441bc627e54234355d","target":"graph","created_at":"2026-07-05T10:27:57Z","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/2503.07493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose V2Flow, a novel tokenizer that produces discrete visual tokens capable of high-fidelity reconstruction, while ensuring structural and latent distribution alignment with the vocabulary space of large language models (LLMs). Leveraging this tight visual-vocabulary coupling, V2Flow enables autoregressive visual generation on top of existing LLMs. Our approach formulates visual tokenization as a flow-matching problem, aiming to learn a mapping from a standard normal prior to the continuous image distribution, conditioned on token sequences embedded within the LLMs vocabulary space. The ","authors_text":"Biye Li, Guiwei Zhang, Mohan Zhou, Tianyu Zhang, Yalong Bai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T16:12:50Z","title":"V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07493","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":"sha256:6f9e9e3e0641db06a42236ece1d69d404637ae81e68afff317df37a95273144a","target":"record","created_at":"2026-07-05T10:27:57Z","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":"458e933f547f22d56c3c5954b2d3950866b96b2877ac04de571a55162f3a463a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T16:12:50Z","title_canon_sha256":"397e5cf7550ccda652b003747657d81812138abed249a389a7fac6793033d572"},"schema_version":"1.0","source":{"id":"2503.07493","kind":"arxiv","version":1}},"canonical_sha256":"5f7fd2466a70520ceba17d1450e2b5818ad83372590a8a260a8f5282c9917423","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f7fd2466a70520ceba17d1450e2b5818ad83372590a8a260a8f5282c9917423","first_computed_at":"2026-07-05T10:27:57.593626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:57.593626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oO/h2/ziMuOAm8q8k/57+ifLz3O+xIHzv/2wIjEPR7Qp/XqfPSP7DJmtbv1cKlltV28jNUxg5jDNmlAIOibyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:57.594163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f9e9e3e0641db06a42236ece1d69d404637ae81e68afff317df37a95273144a","sha256:1b9f5d7a0306b0eac946ceb609a5c76bf5fa29da789538441bc627e54234355d"],"state_sha256":"296a53979c76c6cef8cc083115adc7efa0302835c7bef3a476fa911d05eb8462"}