{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DDJEWDMGCGOKBASBCY6DK5T7O7","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":"9d7ee44c0177d4ae489bd4a99547d270638be2cc0641fba16b2af25161732651","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T16:12:12Z","title_canon_sha256":"93fd8cb39a54022a5c131ffc7b33153fb57a8559219a22c27a852dd3e3b86add"},"schema_version":"1.0","source":{"id":"2409.16211","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16211","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16211v2","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16211","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"DDJEWDMGCGOK","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"pith_short_16","alias_value":"DDJEWDMGCGOKBASB","created_at":"2026-07-05T09:45:55Z"},{"alias_kind":"pith_short_8","alias_value":"DDJEWDMG","created_at":"2026-07-05T09:45:55Z"}],"graph_snapshots":[{"event_id":"sha256:6daad73b5dcb4de50a82829f94581346dd086c0587aceeaacc3171868564b982","target":"graph","created_at":"2026-07-05T09:45:55Z","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/2409.16211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked transformer models for class-conditional image generation have become a compelling alternative to diffusion models. Typically comprising two stages - an initial VQGAN model for transitioning between latent space and image space, and a subsequent Transformer model for image generation within latent space - these frameworks offer promising avenues for image synthesis. In this study, we present two primary contributions: Firstly, an empirical and systematic examination of VQGANs, leading to a modernized VQGAN. Secondly, a novel embedding-free generation network operating directly on bit to","authors_text":"Daniel Cremers, Liang-Chieh Chen, Lijun Yu, Mark Weber, Qihang Yu, Xiaohui Shen, Xueqing Deng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T16:12:12Z","title":"MaskBit: Embedding-free Image Generation via Bit Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16211","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:f0572601004abc0b9057ab1eb61ce6eb8ceba93c7b482c847b0f801449a7806b","target":"record","created_at":"2026-07-05T09:45:55Z","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":"9d7ee44c0177d4ae489bd4a99547d270638be2cc0641fba16b2af25161732651","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T16:12:12Z","title_canon_sha256":"93fd8cb39a54022a5c131ffc7b33153fb57a8559219a22c27a852dd3e3b86add"},"schema_version":"1.0","source":{"id":"2409.16211","kind":"arxiv","version":2}},"canonical_sha256":"18d24b0d86119ca08241163c35767f77d8e8f1597a611696f3bedaf08936ede5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18d24b0d86119ca08241163c35767f77d8e8f1597a611696f3bedaf08936ede5","first_computed_at":"2026-07-05T09:45:55.154808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:55.154808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gijwRoxFnRc1olS5QyPIhL8tU+mV9yNywFp0DPgcb78rk18Su5hT4EExXZO6g2nV5Eg0KnEMjnjQZ1VMw37eCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:55.155288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16211","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0572601004abc0b9057ab1eb61ce6eb8ceba93c7b482c847b0f801449a7806b","sha256:6daad73b5dcb4de50a82829f94581346dd086c0587aceeaacc3171868564b982"],"state_sha256":"6bdca39cfd3a77c14316a957348791fd2a0bbda3b1a059ccd2f908e86ecff6af"}