{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J6SW2KQYYETOVU3L7CKB6O4MO7","short_pith_number":"pith:J6SW2KQY","schema_version":"1.0","canonical_sha256":"4fa56d2a18c126ead36bf8941f3b8c77d1c4d50a6eb26edfe5f2aff56dded741","source":{"kind":"arxiv","id":"2501.07730","version":2},"attestation_state":"computed","paper":{"title":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglin Yang, Dongwon Kim, Ju He, Liang-Chieh Chen, Qihang Yu, Suha Kwak, Xiaohui Shen","submitted_at":"2025-01-13T22:37:17Z","abstract_excerpt":"Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large-scale, high-quality private datasets, making them challenging to replicate. In this work, we introduce Text-Aware Transformer-based 1-Dimensional Tokenizer (TA-TiTok), an efficient and powerful image tokenizer that can utilize either discrete or continuous 1-dimensional tokens. TA-TiTok uniquely integrates textual information during the tokenizer decoding stage (i.e., de-tokenization), accelerating convergence and e"},"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":"2501.07730","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T22:37:17Z","cross_cats_sorted":[],"title_canon_sha256":"d09b7638f50bbc565d45c1d5194066ae0da7ea73532fa6c96c51a96168f30227","abstract_canon_sha256":"dec28741650ff77e45f8a69d1999da1def264bb0a0868210ced9994c1a632b9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:17.855365Z","signature_b64":"SXUgC8yHK0vdIoZ5p6eVMR2bxjAIaj4P+0Y4FsIEU9pC1ISIQkbj/pYfUtKCnnKLnkTk4T5cBuqcPtrdlpUyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fa56d2a18c126ead36bf8941f3b8c77d1c4d50a6eb26edfe5f2aff56dded741","last_reissued_at":"2026-07-05T11:47:17.854838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:17.854838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglin Yang, Dongwon Kim, Ju He, Liang-Chieh Chen, Qihang Yu, Suha Kwak, Xiaohui Shen","submitted_at":"2025-01-13T22:37:17Z","abstract_excerpt":"Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large-scale, high-quality private datasets, making them challenging to replicate. In this work, we introduce Text-Aware Transformer-based 1-Dimensional Tokenizer (TA-TiTok), an efficient and powerful image tokenizer that can utilize either discrete or continuous 1-dimensional tokens. TA-TiTok uniquely integrates textual information during the tokenizer decoding stage (i.e., de-tokenization), accelerating convergence and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07730","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/2501.07730/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":"2501.07730","created_at":"2026-07-05T11:47:17.854893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07730v2","created_at":"2026-07-05T11:47:17.854893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07730","created_at":"2026-07-05T11:47:17.854893+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6SW2KQYYETO","created_at":"2026-07-05T11:47:17.854893+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6SW2KQYYETOVU3L","created_at":"2026-07-05T11:47:17.854893+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6SW2KQY","created_at":"2026-07-05T11:47:17.854893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18518","citing_title":"UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12303","citing_title":"From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05552","citing_title":"Balancing Image Compression and Generation with Bootstrapped Tokenization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06137","citing_title":"Autoregressive Visual Generation Needs a Prologue","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26089","citing_title":"Channel-wise Vector Quantization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30904","citing_title":"MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.00918","citing_title":"Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards","ref_index":29,"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06137","citing_title":"Autoregressive Visual Generation Needs a Prologue","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18518","citing_title":"UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6SW2KQYYETOVU3L7CKB6O4MO7","json":"https://pith.science/pith/J6SW2KQYYETOVU3L7CKB6O4MO7.json","graph_json":"https://pith.science/api/pith-number/J6SW2KQYYETOVU3L7CKB6O4MO7/graph.json","events_json":"https://pith.science/api/pith-number/J6SW2KQYYETOVU3L7CKB6O4MO7/events.json","paper":"https://pith.science/paper/J6SW2KQY"},"agent_actions":{"view_html":"https://pith.science/pith/J6SW2KQYYETOVU3L7CKB6O4MO7","download_json":"https://pith.science/pith/J6SW2KQYYETOVU3L7CKB6O4MO7.json","view_paper":"https://pith.science/paper/J6SW2KQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07730&json=true","fetch_graph":"https://pith.science/api/pith-number/J6SW2KQYYETOVU3L7CKB6O4MO7/graph.json","fetch_events":"https://pith.science/api/pith-number/J6SW2KQYYETOVU3L7CKB6O4MO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6SW2KQYYETOVU3L7CKB6O4MO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6SW2KQYYETOVU3L7CKB6O4MO7/action/storage_attestation","attest_author":"https://pith.science/pith/J6SW2KQYYETOVU3L7CKB6O4MO7/action/author_attestation","sign_citation":"https://pith.science/pith/J6SW2KQYYETOVU3L7CKB6O4MO7/action/citation_signature","submit_replication":"https://pith.science/pith/J6SW2KQYYETOVU3L7CKB6O4MO7/action/replication_record"}},"created_at":"2026-07-05T11:47:17.854893+00:00","updated_at":"2026-07-05T11:47:17.854893+00:00"}