{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DDJEWDMGCGOKBASBCY6DK5T7O7","short_pith_number":"pith:DDJEWDMG","schema_version":"1.0","canonical_sha256":"18d24b0d86119ca08241163c35767f77d8e8f1597a611696f3bedaf08936ede5","source":{"kind":"arxiv","id":"2409.16211","version":2},"attestation_state":"computed","paper":{"title":"MaskBit: Embedding-free Image Generation via Bit Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Cremers, Liang-Chieh Chen, Lijun Yu, Mark Weber, Qihang Yu, Xiaohui Shen, Xueqing Deng","submitted_at":"2024-09-24T16:12:12Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.16211","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T16:12:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"93fd8cb39a54022a5c131ffc7b33153fb57a8559219a22c27a852dd3e3b86add","abstract_canon_sha256":"9d7ee44c0177d4ae489bd4a99547d270638be2cc0641fba16b2af25161732651"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:55.155288Z","signature_b64":"gijwRoxFnRc1olS5QyPIhL8tU+mV9yNywFp0DPgcb78rk18Su5hT4EExXZO6g2nV5Eg0KnEMjnjQZ1VMw37eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18d24b0d86119ca08241163c35767f77d8e8f1597a611696f3bedaf08936ede5","last_reissued_at":"2026-07-05T09:45:55.154808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:55.154808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaskBit: Embedding-free Image Generation via Bit Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Cremers, Liang-Chieh Chen, Lijun Yu, Mark Weber, Qihang Yu, Xiaohui Shen, Xueqing Deng","submitted_at":"2024-09-24T16:12:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16211","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.16211/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.16211","created_at":"2026-07-05T09:45:55.154871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16211v2","created_at":"2026-07-05T09:45:55.154871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16211","created_at":"2026-07-05T09:45:55.154871+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDJEWDMGCGOK","created_at":"2026-07-05T09:45:55.154871+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDJEWDMGCGOKBASB","created_at":"2026-07-05T09:45:55.154871+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDJEWDMG","created_at":"2026-07-05T09:45:55.154871+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07185","citing_title":"AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00371","citing_title":"MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05552","citing_title":"Balancing Image Compression and Generation with Bootstrapped Tokenization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05068","citing_title":"MaCo-GAN: Manifold-Contrastive Adversarial Learning for Single Image Super-Resolution","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17069","citing_title":"Distilling Specialized Orders for Visual Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24885","citing_title":"VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09168","citing_title":"ELT: Elastic Looped Transformers for Visual Generation","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07422","citing_title":"Multimodal Large Language Models for Multi-Subject In-Context Image Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15521","citing_title":"Frequency-Aware Flow Matching for High-Quality Image Generation","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDJEWDMGCGOKBASBCY6DK5T7O7","json":"https://pith.science/pith/DDJEWDMGCGOKBASBCY6DK5T7O7.json","graph_json":"https://pith.science/api/pith-number/DDJEWDMGCGOKBASBCY6DK5T7O7/graph.json","events_json":"https://pith.science/api/pith-number/DDJEWDMGCGOKBASBCY6DK5T7O7/events.json","paper":"https://pith.science/paper/DDJEWDMG"},"agent_actions":{"view_html":"https://pith.science/pith/DDJEWDMGCGOKBASBCY6DK5T7O7","download_json":"https://pith.science/pith/DDJEWDMGCGOKBASBCY6DK5T7O7.json","view_paper":"https://pith.science/paper/DDJEWDMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16211&json=true","fetch_graph":"https://pith.science/api/pith-number/DDJEWDMGCGOKBASBCY6DK5T7O7/graph.json","fetch_events":"https://pith.science/api/pith-number/DDJEWDMGCGOKBASBCY6DK5T7O7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDJEWDMGCGOKBASBCY6DK5T7O7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDJEWDMGCGOKBASBCY6DK5T7O7/action/storage_attestation","attest_author":"https://pith.science/pith/DDJEWDMGCGOKBASBCY6DK5T7O7/action/author_attestation","sign_citation":"https://pith.science/pith/DDJEWDMGCGOKBASBCY6DK5T7O7/action/citation_signature","submit_replication":"https://pith.science/pith/DDJEWDMGCGOKBASBCY6DK5T7O7/action/replication_record"}},"created_at":"2026-07-05T09:45:55.154871+00:00","updated_at":"2026-07-05T09:45:55.154871+00:00"}