{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RUCVRZSJJ6ITTVT43XWE6VLJYM","short_pith_number":"pith:RUCVRZSJ","canonical_record":{"source":{"id":"2501.03120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T16:28:47Z","cross_cats_sorted":[],"title_canon_sha256":"5baf515c7d698373f457e4f22a78b563119148483df8a91bd7cd94fbcb6f80a6","abstract_canon_sha256":"bcee4a297f72b8e49955963cb28b002d0661e34c0d609d6f2862f78e4f827e37"},"schema_version":"1.0"},"canonical_sha256":"8d0558e6494f9139d67cddec4f5569c31a0af6ae750a08a96b11c28d231f0a32","source":{"kind":"arxiv","id":"2501.03120","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03120","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03120v1","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03120","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"RUCVRZSJJ6IT","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"pith_short_16","alias_value":"RUCVRZSJJ6ITTVT4","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"pith_short_8","alias_value":"RUCVRZSJ","created_at":"2026-07-05T09:57:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RUCVRZSJJ6ITTVT43XWE6VLJYM","target":"record","payload":{"canonical_record":{"source":{"id":"2501.03120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T16:28:47Z","cross_cats_sorted":[],"title_canon_sha256":"5baf515c7d698373f457e4f22a78b563119148483df8a91bd7cd94fbcb6f80a6","abstract_canon_sha256":"bcee4a297f72b8e49955963cb28b002d0661e34c0d609d6f2862f78e4f827e37"},"schema_version":"1.0"},"canonical_sha256":"8d0558e6494f9139d67cddec4f5569c31a0af6ae750a08a96b11c28d231f0a32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:31.943845Z","signature_b64":"RYvNL9bxdTbGo/CN+Knc/csGVkRr7E2Jv/xvRBj5es+znIe7g8awyi9fcfhophW3XQ+QNScdmckcYthd6wneBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d0558e6494f9139d67cddec4f5569c31a0af6ae750a08a96b11c28d231f0a32","last_reissued_at":"2026-07-05T09:57:31.943407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:31.943407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.03120","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qf+lflwxQvbwcP/WCV4wjSO9XZrPJ9CBiUlqfyGUNO1tSVxrApL97L+a5nHICQ4fuvat1N7Zure0a8GmaaFpAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:09:47.920034Z"},"content_sha256":"16dde73c16e4be60a0d46eabcea078144fbe366995bda9c802b341097170df83","schema_version":"1.0","event_id":"sha256:16dde73c16e4be60a0d46eabcea078144fbe366995bda9c802b341097170df83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RUCVRZSJJ6ITTVT43XWE6VLJYM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAT: Content-Adaptive Image Tokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunting Zhou, Ishan Misra, Junhong Shen, Kushal Tirumala, Lili Yu, Luke Zettlemoyer, Michihiro Yasunaga","submitted_at":"2025-01-06T16:28:47Z","abstract_excerpt":"Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts representation capacity based on the image content and encodes simpler images into fewer tokens. We design a caption-based evaluation system that leverages large language models (LLMs) to predict content complexity and determine the optimal compression ratio for a given image, taking into account factors critical to human perception. Trained on images with divers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03120","kind":"arxiv","version":1},"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/2501.03120/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":"2026-07-05T09:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dlnsaEg6j46ol6z+MDumJhbPwQJyclTKxss4/qJP4V6X9drWcyAGrpCnE284FGktMH8ju+xiMwG5ZIEnfkEACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:09:47.920405Z"},"content_sha256":"d4e95893e51787fe20e4bdd92dedfe73fe02a970088236ceaae4e6335ab677dd","schema_version":"1.0","event_id":"sha256:d4e95893e51787fe20e4bdd92dedfe73fe02a970088236ceaae4e6335ab677dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RUCVRZSJJ6ITTVT43XWE6VLJYM/bundle.json","state_url":"https://pith.science/pith/RUCVRZSJJ6ITTVT43XWE6VLJYM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RUCVRZSJJ6ITTVT43XWE6VLJYM/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":"2026-08-21T06:09:47Z","links":{"resolver":"https://pith.science/pith/RUCVRZSJJ6ITTVT43XWE6VLJYM","bundle":"https://pith.science/pith/RUCVRZSJJ6ITTVT43XWE6VLJYM/bundle.json","state":"https://pith.science/pith/RUCVRZSJJ6ITTVT43XWE6VLJYM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RUCVRZSJJ6ITTVT43XWE6VLJYM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RUCVRZSJJ6ITTVT43XWE6VLJYM","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":"bcee4a297f72b8e49955963cb28b002d0661e34c0d609d6f2862f78e4f827e37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T16:28:47Z","title_canon_sha256":"5baf515c7d698373f457e4f22a78b563119148483df8a91bd7cd94fbcb6f80a6"},"schema_version":"1.0","source":{"id":"2501.03120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03120","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03120v1","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03120","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"RUCVRZSJJ6IT","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"pith_short_16","alias_value":"RUCVRZSJJ6ITTVT4","created_at":"2026-07-05T09:57:31Z"},{"alias_kind":"pith_short_8","alias_value":"RUCVRZSJ","created_at":"2026-07-05T09:57:31Z"}],"graph_snapshots":[{"event_id":"sha256:d4e95893e51787fe20e4bdd92dedfe73fe02a970088236ceaae4e6335ab677dd","target":"graph","created_at":"2026-07-05T09:57:31Z","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/2501.03120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts representation capacity based on the image content and encodes simpler images into fewer tokens. We design a caption-based evaluation system that leverages large language models (LLMs) to predict content complexity and determine the optimal compression ratio for a given image, taking into account factors critical to human perception. Trained on images with divers","authors_text":"Chunting Zhou, Ishan Misra, Junhong Shen, Kushal Tirumala, Lili Yu, Luke Zettlemoyer, Michihiro Yasunaga","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T16:28:47Z","title":"CAT: Content-Adaptive Image Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03120","kind":"arxiv","version":1},"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":"sha256:16dde73c16e4be60a0d46eabcea078144fbe366995bda9c802b341097170df83","target":"record","created_at":"2026-07-05T09:57:31Z","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":"bcee4a297f72b8e49955963cb28b002d0661e34c0d609d6f2862f78e4f827e37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T16:28:47Z","title_canon_sha256":"5baf515c7d698373f457e4f22a78b563119148483df8a91bd7cd94fbcb6f80a6"},"schema_version":"1.0","source":{"id":"2501.03120","kind":"arxiv","version":1}},"canonical_sha256":"8d0558e6494f9139d67cddec4f5569c31a0af6ae750a08a96b11c28d231f0a32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d0558e6494f9139d67cddec4f5569c31a0af6ae750a08a96b11c28d231f0a32","first_computed_at":"2026-07-05T09:57:31.943407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:31.943407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RYvNL9bxdTbGo/CN+Knc/csGVkRr7E2Jv/xvRBj5es+znIe7g8awyi9fcfhophW3XQ+QNScdmckcYthd6wneBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:31.943845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16dde73c16e4be60a0d46eabcea078144fbe366995bda9c802b341097170df83","sha256:d4e95893e51787fe20e4bdd92dedfe73fe02a970088236ceaae4e6335ab677dd"],"state_sha256":"70abd898ed367aef240264e0740ab30a1152c65495fbf127d19939d3500e1151"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/nxpf1xUefgYOkWokNIMFUcS4OY37kbJDHwrfVWYWn50Gk7d8wzDvmjLF2iJmCBm9wBaec8mhKAwPHJGuEFqCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T06:09:47.922643Z","bundle_sha256":"14e03e4177e6e8ddf0aa04114ef515488735d9ea01620ec21424d25c392fff83"}}