{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OBA74JHRBHJZMGFREO25BIHWMA","short_pith_number":"pith:OBA74JHR","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"},"canonical_sha256":"7041fe24f109d39618b123b5d0a0f66023d5037ba3e1242d47e367decf0856c6","source":{"kind":"arxiv","id":"2412.05796","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05796","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05796v2","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05796","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"OBA74JHRBHJZ","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_16","alias_value":"OBA74JHRBHJZMGFR","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_8","alias_value":"OBA74JHR","created_at":"2026-07-05T10:44:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OBA74JHRBHJZMGFREO25BIHWMA","target":"record","payload":{"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"},"canonical_sha256":"7041fe24f109d39618b123b5d0a0f66023d5037ba3e1242d47e367decf0856c6","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"},"source_kind":"arxiv","source_id":"2412.05796","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MZ9f4jRHndJHtyRc3dnDyXA2StIAhoSyRAkEFaYdVWUPQPyRzAOg52a4qmDxRgdJ3KBvDVp4bla8vg7PYw7qDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:59:38.037824Z"},"content_sha256":"e7c73450fd0051d734681253ce470881dc1aaf870e83ba907829d929a10a4212","schema_version":"1.0","event_id":"sha256:e7c73450fd0051d734681253ce470881dc1aaf870e83ba907829d929a10a4212"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OBA74JHRBHJZMGFREO25BIHWMA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ymAG5b7DOwyiTUUrVZPGK9Zbbz0xQN/zgkU7h69j9mwDltU6eDJjV69O07D4cHNoWU3fMJua8SnSd/LmwMXmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:59:38.041406Z"},"content_sha256":"44c76a4803131bad4567affdfb2d92047944427c04ceb14055987813361c6142","schema_version":"1.0","event_id":"sha256:44c76a4803131bad4567affdfb2d92047944427c04ceb14055987813361c6142"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA/bundle.json","state_url":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OBA74JHRBHJZMGFREO25BIHWMA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T15:59:38Z","links":{"resolver":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA","bundle":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA/bundle.json","state":"https://pith.science/pith/OBA74JHRBHJZMGFREO25BIHWMA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OBA74JHRBHJZMGFREO25BIHWMA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OBA74JHRBHJZMGFREO25BIHWMA","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":"3f517f50bfdd2e03e14ea23f00ca48eb4c6a8e1ed1396fb06dc418759aac60f0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T03:18:17Z","title_canon_sha256":"063d534023abef47dd2214914cb5a9504e4eb061b6ba0fa17828dc4675d4ed9a"},"schema_version":"1.0","source":{"id":"2412.05796","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05796","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05796v2","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05796","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"OBA74JHRBHJZ","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_16","alias_value":"OBA74JHRBHJZMGFR","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_8","alias_value":"OBA74JHR","created_at":"2026-07-05T10:44:41Z"}],"graph_snapshots":[{"event_id":"sha256:44c76a4803131bad4567affdfb2d92047944427c04ceb14055987813361c6142","target":"graph","created_at":"2026-07-05T10:44:41Z","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/2412.05796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alireza Fathi, Cordelia Schmid, David A. Ross, Dina Katabi, Kaiwen Zha, Lijun Yu, Xiuye Gu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T03:18:17Z","title":"Language-Guided Image Tokenization for Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05796","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:e7c73450fd0051d734681253ce470881dc1aaf870e83ba907829d929a10a4212","target":"record","created_at":"2026-07-05T10:44:41Z","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":"3f517f50bfdd2e03e14ea23f00ca48eb4c6a8e1ed1396fb06dc418759aac60f0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T03:18:17Z","title_canon_sha256":"063d534023abef47dd2214914cb5a9504e4eb061b6ba0fa17828dc4675d4ed9a"},"schema_version":"1.0","source":{"id":"2412.05796","kind":"arxiv","version":2}},"canonical_sha256":"7041fe24f109d39618b123b5d0a0f66023d5037ba3e1242d47e367decf0856c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7041fe24f109d39618b123b5d0a0f66023d5037ba3e1242d47e367decf0856c6","first_computed_at":"2026-07-05T10:44:41.907209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:41.907209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2RYddGGtQ5c2+1P3TnYru8iR5dLbOOo0k4JRXXz4KlE7ryeJPF9S8fR78yEFJWXAAls/migEtUyRZqvwDFwjAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:41.907716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05796","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7c73450fd0051d734681253ce470881dc1aaf870e83ba907829d929a10a4212","sha256:44c76a4803131bad4567affdfb2d92047944427c04ceb14055987813361c6142"],"state_sha256":"33bb3e36a05696735602a87ab6d8f250c18b5c9cc89b350456be4fbd1409ec0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RHx98GK1H7valUMSKga0ltnfb2E2GbDFnEWeoNFJ8lCjBdCDoWT3ZrKzQdIn0cIoUlBdw7lr0ATKBXrj9z8aDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:59:38.099457Z","bundle_sha256":"3d28ebce76f4e050bbb53a512ac2539f21e5165ec8c0a2bc5ff5ab9c5d7488ae"}}