{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FN6NOUFFTYV34HLUJVZFARW3YI","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":"b46877db1112f0010d3fad9e27da22fd6cb8420390a2e30c1c1324f7a107d669","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-16T18:59:04Z","title_canon_sha256":"798139dcea2b5fe2fada30bd83c19c07dcb5ac8bc5ac8b7877a2c47263d1c8ac"},"schema_version":"1.0","source":{"id":"2501.09755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09755","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09755v1","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09755","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"FN6NOUFFTYV3","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"FN6NOUFFTYV34HLU","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"FN6NOUFF","created_at":"2026-07-05T10:01:58Z"}],"graph_snapshots":[{"event_id":"sha256:52d52c88b2d198d2d9491fc1bea41914c45fafb7db298f1d321d10a7f077e60a","target":"graph","created_at":"2026-07-05T10:01:58Z","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/2501.09755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual tokenization via auto-encoding empowers state-of-the-art image and video generative models by compressing pixels into a latent space. Although scaling Transformer-based generators has been central to recent advances, the tokenizer component itself is rarely scaled, leaving open questions about how auto-encoder design choices influence both its objective of reconstruction and downstream generative performance. Our work aims to conduct an exploration of scaling in auto-encoders to fill in this blank. To facilitate this exploration, we replace the typical convolutional backbone with an enh","authors_text":"Ching-Yao Chung, David Yan, Jialiang Wang, Orr Zohar, Peter Vajda, Philippe Hansen-Estruch, Sriram Vishwanath, Tao Xu, Tingbo Hou, Xinlei Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-16T18:59:04Z","title":"Learnings from Scaling Visual Tokenizers for Reconstruction and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09755","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":"sha256:9e991b90b634bc16591599a7f6e9f150669983b5d2f687b8c44e5225ce5435c2","target":"record","created_at":"2026-07-05T10:01:58Z","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":"b46877db1112f0010d3fad9e27da22fd6cb8420390a2e30c1c1324f7a107d669","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-16T18:59:04Z","title_canon_sha256":"798139dcea2b5fe2fada30bd83c19c07dcb5ac8bc5ac8b7877a2c47263d1c8ac"},"schema_version":"1.0","source":{"id":"2501.09755","kind":"arxiv","version":1}},"canonical_sha256":"2b7cd750a59e2bbe1d744d725046dbc218dca98dc0145b8399499691567ff514","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b7cd750a59e2bbe1d744d725046dbc218dca98dc0145b8399499691567ff514","first_computed_at":"2026-07-05T10:01:58.115859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:58.115859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"keUi8HRGJ8rxl34qLcjd6pL8pB8vcEVLyUv3NELe8zOqTRM6RsYFDpmTHE9ebtSZp2TiAA0yFBZtSC/rH+NnBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:58.116335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e991b90b634bc16591599a7f6e9f150669983b5d2f687b8c44e5225ce5435c2","sha256:52d52c88b2d198d2d9491fc1bea41914c45fafb7db298f1d321d10a7f077e60a"],"state_sha256":"f78a1617921311de88de1a3423a0e5596bc7bc94c4c5f9242b1e78ef3afb456b"}