{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OBA74JHRBHJZMGFREO25BIHWMA","short_pith_number":"pith:OBA74JHR","schema_version":"1.0","canonical_sha256":"7041fe24f109d39618b123b5d0a0f66023d5037ba3e1242d47e367decf0856c6","source":{"kind":"arxiv","id":"2412.05796","version":2},"attestation_state":"computed","paper":{"title":"Language-Guided Image Tokenization for Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alireza Fathi, Cordelia Schmid, David A. Ross, Dina Katabi, Kaiwen Zha, Lijun Yu, Xiuye Gu","submitted_at":"2024-12-08T03:18:17Z","abstract_excerpt":"Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally have limited compression rates, making high-resolution image generation computationally expensive. To address this challenge, we propose to leverage language for efficient image tokenization, and we call our method Text-Conditioned Image Tokenization (TexTok). TexTok is a simple yet effective tokenization framework that leverages language to provide a compac"},"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":"2412.05796","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T03:18:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"063d534023abef47dd2214914cb5a9504e4eb061b6ba0fa17828dc4675d4ed9a","abstract_canon_sha256":"3f517f50bfdd2e03e14ea23f00ca48eb4c6a8e1ed1396fb06dc418759aac60f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:41.907716Z","signature_b64":"2RYddGGtQ5c2+1P3TnYru8iR5dLbOOo0k4JRXXz4KlE7ryeJPF9S8fR78yEFJWXAAls/migEtUyRZqvwDFwjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7041fe24f109d39618b123b5d0a0f66023d5037ba3e1242d47e367decf0856c6","last_reissued_at":"2026-07-05T10:44:41.907209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:41.907209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Guided Image Tokenization for Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alireza Fathi, Cordelia Schmid, David A. Ross, Dina Katabi, Kaiwen Zha, Lijun Yu, Xiuye Gu","submitted_at":"2024-12-08T03:18:17Z","abstract_excerpt":"Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally have limited compression rates, making high-resolution image generation computationally expensive. To address this challenge, we propose to leverage language for efficient image tokenization, and we call our method Text-Conditioned Image Tokenization (TexTok). TexTok is a simple yet effective tokenization framework that leverages language to provide a compac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05796","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/2412.05796/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":"2412.05796","created_at":"2026-07-05T10:44:41.907268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05796v2","created_at":"2026-07-05T10:44:41.907268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05796","created_at":"2026-07-05T10:44:41.907268+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBA74JHRBHJZ","created_at":"2026-07-05T10:44:41.907268+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBA74JHRBHJZMGFR","created_at":"2026-07-05T10:44:41.907268+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBA74JHR","created_at":"2026-07-05T10:44:41.907268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06111","citing_title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA","json":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA.json","graph_json":"https://pith.science/api/pith-number/OBA74JHRBHJZMGFREO25BIHWMA/graph.json","events_json":"https://pith.science/api/pith-number/OBA74JHRBHJZMGFREO25BIHWMA/events.json","paper":"https://pith.science/paper/OBA74JHR"},"agent_actions":{"view_html":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA","download_json":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA.json","view_paper":"https://pith.science/paper/OBA74JHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05796&json=true","fetch_graph":"https://pith.science/api/pith-number/OBA74JHRBHJZMGFREO25BIHWMA/graph.json","fetch_events":"https://pith.science/api/pith-number/OBA74JHRBHJZMGFREO25BIHWMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA/action/storage_attestation","attest_author":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA/action/author_attestation","sign_citation":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA/action/citation_signature","submit_replication":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA/action/replication_record"}},"created_at":"2026-07-05T10:44:41.907268+00:00","updated_at":"2026-07-05T10:44:41.907268+00:00"}