{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B7SYAUWZCTZ7ZJJQ3IUO6ISKVL","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":"bc7f7dc9d6cc3b2154e7224b1235a6051cf2973b1d5e9ae652c9acb265fba67d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T06:04:40Z","title_canon_sha256":"4c2bbb3924c93527a2c4cf946edcc25a077829f76532e1a1612990de7b117db1"},"schema_version":"1.0","source":{"id":"2405.14206","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14206","created_at":"2026-07-05T09:17:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14206v2","created_at":"2026-07-05T09:17:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14206","created_at":"2026-07-05T09:17:42Z"},{"alias_kind":"pith_short_12","alias_value":"B7SYAUWZCTZ7","created_at":"2026-07-05T09:17:42Z"},{"alias_kind":"pith_short_16","alias_value":"B7SYAUWZCTZ7ZJJQ","created_at":"2026-07-05T09:17:42Z"},{"alias_kind":"pith_short_8","alias_value":"B7SYAUWZ","created_at":"2026-07-05T09:17:42Z"}],"graph_snapshots":[{"event_id":"sha256:6082ca368681143e4810b418183b54fd7ce7a3282e407e7cbefe15f9cc76a285","target":"graph","created_at":"2026-07-05T09:17:42Z","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/2405.14206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vector quantization (VQ) is a key technique in high-resolution and high-fidelity image synthesis, which aims to learn a codebook to encode an image with a sequence of discrete codes and then generate an image in an auto-regression manner. Although existing methods have shown superior performance, most methods prefer to learn a single-modal codebook (\\emph{e.g.}, image), resulting in suboptimal performance when the codebook is applied to multi-modal downstream tasks (\\emph{e.g.}, text-to-image, image captioning) due to the existence of modal gaps. In this paper, we propose a novel language-guid","authors_text":"Baoquan Zhang, Chuyao Luo, Guotao Liang, Huaibin Wang, Kola Ye, linfeng Luo, Xutao Li, Yaowei Wang, Yunming Ye","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T06:04:40Z","title":"LG-VQ: Language-Guided Codebook Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14206","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":"sha256:1ce10d0d4e5b9762dd3fc3d07bb4244b05b9b947804d1415e62e98b6a91c94c9","target":"record","created_at":"2026-07-05T09:17:42Z","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":"bc7f7dc9d6cc3b2154e7224b1235a6051cf2973b1d5e9ae652c9acb265fba67d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T06:04:40Z","title_canon_sha256":"4c2bbb3924c93527a2c4cf946edcc25a077829f76532e1a1612990de7b117db1"},"schema_version":"1.0","source":{"id":"2405.14206","kind":"arxiv","version":2}},"canonical_sha256":"0fe58052d914f3fca530da28ef224aaade6ef2d3ce9c63b35a3888ab1a356f15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fe58052d914f3fca530da28ef224aaade6ef2d3ce9c63b35a3888ab1a356f15","first_computed_at":"2026-07-05T09:17:42.215440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:42.215440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pSbZEX8ouxwsgy9dS04j4pc45mBwWME1Hw0C3jo6/jZrHxs4mO+UVyDmeUgxrBOQ/wD/1bHZ72Dm7895ITSsCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:42.215908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14206","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ce10d0d4e5b9762dd3fc3d07bb4244b05b9b947804d1415e62e98b6a91c94c9","sha256:6082ca368681143e4810b418183b54fd7ce7a3282e407e7cbefe15f9cc76a285"],"state_sha256":"748d7010a106236e859bca97564887750e5a28f1dff49d8539918d50e3489768"}