{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IPOKJRNC4VYGVD442Y7CDJVTKN","short_pith_number":"pith:IPOKJRNC","schema_version":"1.0","canonical_sha256":"43dca4c5a2e5706a8f9cd63e21a6b3535a85f03a1cba5cad8768144c13edb36e","source":{"kind":"arxiv","id":"2410.01756","version":3},"attestation_state":"computed","paper":{"title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhiksha Raj, Hao Chen, Jason Kuen, Jiuxiang Gu, Kai Qiu, Xiang Li, Zhe Lin","submitted_at":"2024-10-02T17:06:39Z","abstract_excerpt":"Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approach to improve the image reconstruction quality. However, tokenizers with longer token lengths are not guaranteed to achieve better generation quality. There exists a trade-off between reconstruction and generation quality regarding token length. In this paper, we investigate the impact of token length on both image reconstruction and generation and provide a flexible solution t"},"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":"2410.01756","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T17:06:39Z","cross_cats_sorted":[],"title_canon_sha256":"61b61b3031cb1d7382bfe9793afb5c3c4a2f07b4a8a4dc4114c129f8d04f055f","abstract_canon_sha256":"8504afd93ad3dd70622c97d8ae9f9ac6a9e8573a8157cde7785da7df9a8a02e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:15.180972Z","signature_b64":"PGXk29tIFAhD4he1kZuXHns8N2rGBBvyrwiKeS/V+/VCofe345h1SCZIg9iEWI83BP6jJW36jeZNVjvcUc/JCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43dca4c5a2e5706a8f9cd63e21a6b3535a85f03a1cba5cad8768144c13edb36e","last_reissued_at":"2026-07-05T09:44:15.180385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:15.180385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhiksha Raj, Hao Chen, Jason Kuen, Jiuxiang Gu, Kai Qiu, Xiang Li, Zhe Lin","submitted_at":"2024-10-02T17:06:39Z","abstract_excerpt":"Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approach to improve the image reconstruction quality. However, tokenizers with longer token lengths are not guaranteed to achieve better generation quality. There exists a trade-off between reconstruction and generation quality regarding token length. In this paper, we investigate the impact of token length on both image reconstruction and generation and provide a flexible solution t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01756","kind":"arxiv","version":3},"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/2410.01756/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":"2410.01756","created_at":"2026-07-05T09:44:15.180456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01756v3","created_at":"2026-07-05T09:44:15.180456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01756","created_at":"2026-07-05T09:44:15.180456+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPOKJRNC4VYG","created_at":"2026-07-05T09:44:15.180456+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPOKJRNC4VYGVD44","created_at":"2026-07-05T09:44:15.180456+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPOKJRNC","created_at":"2026-07-05T09:44:15.180456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13289","citing_title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11096","citing_title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07185","citing_title":"AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens","ref_index":29,"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":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05552","citing_title":"Balancing Image Compression and Generation with Bootstrapped Tokenization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06137","citing_title":"Autoregressive Visual Generation Needs a Prologue","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27696","citing_title":"Structure over Pixels: Learning Variable-Length Visual Programs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31215","citing_title":"Fixed-Point Masked Generative Modeling","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01593","citing_title":"Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18115","citing_title":"WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18390","citing_title":"Vision Foundation Models as Generalist Tokenizers for Image Generation","ref_index":46,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06137","citing_title":"Autoregressive Visual Generation Needs a Prologue","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11707","citing_title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07915","citing_title":"What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPOKJRNC4VYGVD442Y7CDJVTKN","json":"https://pith.science/pith/IPOKJRNC4VYGVD442Y7CDJVTKN.json","graph_json":"https://pith.science/api/pith-number/IPOKJRNC4VYGVD442Y7CDJVTKN/graph.json","events_json":"https://pith.science/api/pith-number/IPOKJRNC4VYGVD442Y7CDJVTKN/events.json","paper":"https://pith.science/paper/IPOKJRNC"},"agent_actions":{"view_html":"https://pith.science/pith/IPOKJRNC4VYGVD442Y7CDJVTKN","download_json":"https://pith.science/pith/IPOKJRNC4VYGVD442Y7CDJVTKN.json","view_paper":"https://pith.science/paper/IPOKJRNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01756&json=true","fetch_graph":"https://pith.science/api/pith-number/IPOKJRNC4VYGVD442Y7CDJVTKN/graph.json","fetch_events":"https://pith.science/api/pith-number/IPOKJRNC4VYGVD442Y7CDJVTKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPOKJRNC4VYGVD442Y7CDJVTKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPOKJRNC4VYGVD442Y7CDJVTKN/action/storage_attestation","attest_author":"https://pith.science/pith/IPOKJRNC4VYGVD442Y7CDJVTKN/action/author_attestation","sign_citation":"https://pith.science/pith/IPOKJRNC4VYGVD442Y7CDJVTKN/action/citation_signature","submit_replication":"https://pith.science/pith/IPOKJRNC4VYGVD442Y7CDJVTKN/action/replication_record"}},"created_at":"2026-07-05T09:44:15.180456+00:00","updated_at":"2026-07-05T09:44:15.180456+00:00"}