{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TYGM2W6NQGGKCZ2I7R2QFBEMJW","short_pith_number":"pith:TYGM2W6N","canonical_record":{"source":{"id":"2505.13439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T17:59:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b225256d88b7142370cf0f0ab3ab8e7ce36b11783339e2c0f80187e21052c0d4","abstract_canon_sha256":"6f859471f6fa505adbfdf05cb101870782fbcb889c033c4467c15a9d7e39ee6d"},"schema_version":"1.0"},"canonical_sha256":"9e0ccd5bcd818ca16748fc7502848c4d8dc6023f6e9e0aabf35b7ba5b5da6ccc","source":{"kind":"arxiv","id":"2505.13439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13439","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13439v1","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13439","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"pith_short_12","alias_value":"TYGM2W6NQGGK","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"pith_short_16","alias_value":"TYGM2W6NQGGKCZ2I","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"pith_short_8","alias_value":"TYGM2W6N","created_at":"2026-07-05T11:05:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TYGM2W6NQGGKCZ2I7R2QFBEMJW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T17:59:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b225256d88b7142370cf0f0ab3ab8e7ce36b11783339e2c0f80187e21052c0d4","abstract_canon_sha256":"6f859471f6fa505adbfdf05cb101870782fbcb889c033c4467c15a9d7e39ee6d"},"schema_version":"1.0"},"canonical_sha256":"9e0ccd5bcd818ca16748fc7502848c4d8dc6023f6e9e0aabf35b7ba5b5da6ccc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:30.187332Z","signature_b64":"eme+IeE2DDk2kBOS5L9LKuomvbiu6ceVdXyfGjVZuDgQIoflbT3IN6l91XJ6wyN4MHdppG2nfM6mAG8osWoCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e0ccd5bcd818ca16748fc7502848c4d8dc6023f6e9e0aabf35b7ba5b5da6ccc","last_reissued_at":"2026-07-05T11:05:30.186835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:30.186835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13439","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":"2026-07-05T11:05:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b7a2W7uBlsL8NwohhCFVLmVONcE5NAT8CJ2g4JxFxCWr4jfDAsgruxDhGu2HN0nrw8IwRcrWRdBmhYM51JJYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:56:10.513359Z"},"content_sha256":"ec59075602e870f3e860d0cd03e187ae42e40d5f4f663f1a30c859b003ef9fa2","schema_version":"1.0","event_id":"sha256:ec59075602e870f3e860d0cd03e187ae42e40d5f4f663f1a30c859b003ef9fa2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TYGM2W6NQGGKCZ2I7R2QFBEMJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Huawei Lin, Tong Geng, Weijie Zhao, Zhaozhuo Xu","submitted_at":"2025-05-19T17:59:01Z","abstract_excerpt":"Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to discrete token sequences. The quality of the VT largely defines the upper bound of AR model performance. However, current discrete VTs fall significantly behind continuous variational autoencoders (VAEs), leading to degraded image reconstructions and poor preservation of details and text. Existing benchmarks focus on end-to-end generation quality, without isolating VT performance. To address this gap, we introduce VT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13439","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/2505.13439/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":"2026-07-05T11:05:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ltrmYBIQIh9EvuUWIbp7bRTJcnSj2epD2uEvs5nRT40tfJbS3g0coDIWDZobSrtM33HzgguqcL1mMdakruI5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:56:10.513941Z"},"content_sha256":"e20b85ade729595c2f6f2cc3e1ad5b0372e9f331c7ef2dfa04b62bd5a5fea147","schema_version":"1.0","event_id":"sha256:e20b85ade729595c2f6f2cc3e1ad5b0372e9f331c7ef2dfa04b62bd5a5fea147"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYGM2W6NQGGKCZ2I7R2QFBEMJW/bundle.json","state_url":"https://pith.science/pith/TYGM2W6NQGGKCZ2I7R2QFBEMJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYGM2W6NQGGKCZ2I7R2QFBEMJW/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":"2026-08-15T00:56:10Z","links":{"resolver":"https://pith.science/pith/TYGM2W6NQGGKCZ2I7R2QFBEMJW","bundle":"https://pith.science/pith/TYGM2W6NQGGKCZ2I7R2QFBEMJW/bundle.json","state":"https://pith.science/pith/TYGM2W6NQGGKCZ2I7R2QFBEMJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYGM2W6NQGGKCZ2I7R2QFBEMJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TYGM2W6NQGGKCZ2I7R2QFBEMJW","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":"6f859471f6fa505adbfdf05cb101870782fbcb889c033c4467c15a9d7e39ee6d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T17:59:01Z","title_canon_sha256":"b225256d88b7142370cf0f0ab3ab8e7ce36b11783339e2c0f80187e21052c0d4"},"schema_version":"1.0","source":{"id":"2505.13439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13439","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13439v1","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13439","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"pith_short_12","alias_value":"TYGM2W6NQGGK","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"pith_short_16","alias_value":"TYGM2W6NQGGKCZ2I","created_at":"2026-07-05T11:05:30Z"},{"alias_kind":"pith_short_8","alias_value":"TYGM2W6N","created_at":"2026-07-05T11:05:30Z"}],"graph_snapshots":[{"event_id":"sha256:e20b85ade729595c2f6f2cc3e1ad5b0372e9f331c7ef2dfa04b62bd5a5fea147","target":"graph","created_at":"2026-07-05T11:05:30Z","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/2505.13439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to discrete token sequences. The quality of the VT largely defines the upper bound of AR model performance. However, current discrete VTs fall significantly behind continuous variational autoencoders (VAEs), leading to degraded image reconstructions and poor preservation of details and text. Existing benchmarks focus on end-to-end generation quality, without isolating VT performance. To address this gap, we introduce VT","authors_text":"Huawei Lin, Tong Geng, Weijie Zhao, Zhaozhuo Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T17:59:01Z","title":"VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13439","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:ec59075602e870f3e860d0cd03e187ae42e40d5f4f663f1a30c859b003ef9fa2","target":"record","created_at":"2026-07-05T11:05:30Z","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":"6f859471f6fa505adbfdf05cb101870782fbcb889c033c4467c15a9d7e39ee6d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T17:59:01Z","title_canon_sha256":"b225256d88b7142370cf0f0ab3ab8e7ce36b11783339e2c0f80187e21052c0d4"},"schema_version":"1.0","source":{"id":"2505.13439","kind":"arxiv","version":1}},"canonical_sha256":"9e0ccd5bcd818ca16748fc7502848c4d8dc6023f6e9e0aabf35b7ba5b5da6ccc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e0ccd5bcd818ca16748fc7502848c4d8dc6023f6e9e0aabf35b7ba5b5da6ccc","first_computed_at":"2026-07-05T11:05:30.186835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:30.186835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eme+IeE2DDk2kBOS5L9LKuomvbiu6ceVdXyfGjVZuDgQIoflbT3IN6l91XJ6wyN4MHdppG2nfM6mAG8osWoCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:30.187332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec59075602e870f3e860d0cd03e187ae42e40d5f4f663f1a30c859b003ef9fa2","sha256:e20b85ade729595c2f6f2cc3e1ad5b0372e9f331c7ef2dfa04b62bd5a5fea147"],"state_sha256":"e92b3366f10ab254002df19bf2e51c9886e7dcbc55e917451861a3e1b0714238"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k1zS5osBAvU5nxrBHpLIWHWmILEJjwBiAbRbn+LM4vX7ZVT3bXFM4DOytEmqM6CDtCpiQPNtRyGR15gNzqtXDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T00:56:10.517330Z","bundle_sha256":"7eaaaa35afcd69bad08710337991a0d3bd564988127c6a98fa37c8f30d4fa6e6"}}