{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6YELJ4GO7LCEBHX3OISMLY3ZBF","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":"7d6fe6696f74890d7bc088855d612ca6b2d2da9a4bef37d97b45e0b97fb6b84f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T20:29:29Z","title_canon_sha256":"04b17a8ab95704fc9820e622f2a1e2de01eecaedf303acdef9674623ef2eef4f"},"schema_version":"1.0","source":{"id":"2412.10958","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10958","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10958v3","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10958","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"6YELJ4GO7LCE","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"pith_short_16","alias_value":"6YELJ4GO7LCEBHX3","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"pith_short_8","alias_value":"6YELJ4GO","created_at":"2026-07-05T10:31:51Z"}],"graph_snapshots":[{"event_id":"sha256:4a5e96ede1260b64007b21a3484a68f197b5e202bdf98bfb28e509b842ebb097","target":"graph","created_at":"2026-07-05T10:31:51Z","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/2412.10958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple codewords into each latent token, substantially increasing the representation capacity of the latent space. When applied to Transformer-based architectures, our approach compresses 256x256 and 512x512 images using as few as 32 or 64 1-dimensional tokens. Not only does SoftVQ-VAE show consistent and high-quality reconstruction, more importantly, it also achieves ","authors_text":"Bhiksha Raj, Emad Barsoum, Fangyi Chen, Hao Chen, Jiang Liu, Jindong Wang, Xiang Li, Ximeng Sun, Ze Wang, Zicheng Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T20:29:29Z","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10958","kind":"arxiv","version":3},"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":"sha256:2a2b2811bb3a2f45daa374ec9e6b77acd885cfc56f6f230563116aeae64ab976","target":"record","created_at":"2026-07-05T10:31:51Z","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":"7d6fe6696f74890d7bc088855d612ca6b2d2da9a4bef37d97b45e0b97fb6b84f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T20:29:29Z","title_canon_sha256":"04b17a8ab95704fc9820e622f2a1e2de01eecaedf303acdef9674623ef2eef4f"},"schema_version":"1.0","source":{"id":"2412.10958","kind":"arxiv","version":3}},"canonical_sha256":"f608b4f0cefac4409efb7224c5e37909518912c24cae237a9e1a3600202eb11a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f608b4f0cefac4409efb7224c5e37909518912c24cae237a9e1a3600202eb11a","first_computed_at":"2026-07-05T10:31:51.735023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:51.735023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GkTEU/Bdtlyo58fPnK3yaAEjp0egZqpNuCWfoSQIltowdRns5W8BRt2wkqURSzelj8Jh/1Nx9QkJHXiT8khbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:51.735548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10958","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a2b2811bb3a2f45daa374ec9e6b77acd885cfc56f6f230563116aeae64ab976","sha256:4a5e96ede1260b64007b21a3484a68f197b5e202bdf98bfb28e509b842ebb097"],"state_sha256":"d8d8973d67b935b0c472729f7041ddd0ce093dd00cf2ed8fcf1efb9e2817acdf"}