{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B7SYAUWZCTZ7ZJJQ3IUO6ISKVL","short_pith_number":"pith:B7SYAUWZ","canonical_record":{"source":{"id":"2405.14206","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T06:04:40Z","cross_cats_sorted":[],"title_canon_sha256":"4c2bbb3924c93527a2c4cf946edcc25a077829f76532e1a1612990de7b117db1","abstract_canon_sha256":"bc7f7dc9d6cc3b2154e7224b1235a6051cf2973b1d5e9ae652c9acb265fba67d"},"schema_version":"1.0"},"canonical_sha256":"0fe58052d914f3fca530da28ef224aaade6ef2d3ce9c63b35a3888ab1a356f15","source":{"kind":"arxiv","id":"2405.14206","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B7SYAUWZCTZ7ZJJQ3IUO6ISKVL","target":"record","payload":{"canonical_record":{"source":{"id":"2405.14206","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T06:04:40Z","cross_cats_sorted":[],"title_canon_sha256":"4c2bbb3924c93527a2c4cf946edcc25a077829f76532e1a1612990de7b117db1","abstract_canon_sha256":"bc7f7dc9d6cc3b2154e7224b1235a6051cf2973b1d5e9ae652c9acb265fba67d"},"schema_version":"1.0"},"canonical_sha256":"0fe58052d914f3fca530da28ef224aaade6ef2d3ce9c63b35a3888ab1a356f15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:42.215908Z","signature_b64":"pSbZEX8ouxwsgy9dS04j4pc45mBwWME1Hw0C3jo6/jZrHxs4mO+UVyDmeUgxrBOQ/wD/1bHZ72Dm7895ITSsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fe58052d914f3fca530da28ef224aaade6ef2d3ce9c63b35a3888ab1a356f15","last_reissued_at":"2026-07-05T09:17:42.215440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:42.215440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.14206","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"91Y99K8ohP6G8xT1SacZ2kBrqTQxACO4DidsjhNnsg3OCJ3/F2nN0KoRVhyAvC6Fb0HW6n2Yca48OxWiKHA+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:00:57.015037Z"},"content_sha256":"1ce10d0d4e5b9762dd3fc3d07bb4244b05b9b947804d1415e62e98b6a91c94c9","schema_version":"1.0","event_id":"sha256:1ce10d0d4e5b9762dd3fc3d07bb4244b05b9b947804d1415e62e98b6a91c94c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B7SYAUWZCTZ7ZJJQ3IUO6ISKVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LG-VQ: Language-Guided Codebook Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoquan Zhang, Chuyao Luo, Guotao Liang, Huaibin Wang, Kola Ye, linfeng Luo, Xutao Li, Yaowei Wang, Yunming Ye","submitted_at":"2024-05-23T06:04:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14206","kind":"arxiv","version":2},"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/2405.14206/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":"2026-07-05T09:17:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8l8OeQml+7V7CqNRL0iw/fbqgQ8gV6drIMSSlHhIpkjCZ2hc4fIpwLiMKniOPM6UGZ4E6i8VJQJOaY0Xn6n/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:00:57.015535Z"},"content_sha256":"6082ca368681143e4810b418183b54fd7ce7a3282e407e7cbefe15f9cc76a285","schema_version":"1.0","event_id":"sha256:6082ca368681143e4810b418183b54fd7ce7a3282e407e7cbefe15f9cc76a285"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B7SYAUWZCTZ7ZJJQ3IUO6ISKVL/bundle.json","state_url":"https://pith.science/pith/B7SYAUWZCTZ7ZJJQ3IUO6ISKVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B7SYAUWZCTZ7ZJJQ3IUO6ISKVL/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":"2026-08-15T04:00:57Z","links":{"resolver":"https://pith.science/pith/B7SYAUWZCTZ7ZJJQ3IUO6ISKVL","bundle":"https://pith.science/pith/B7SYAUWZCTZ7ZJJQ3IUO6ISKVL/bundle.json","state":"https://pith.science/pith/B7SYAUWZCTZ7ZJJQ3IUO6ISKVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B7SYAUWZCTZ7ZJJQ3IUO6ISKVL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jm/nOlzJK9zLquvUWDuat/zU96vXgtpQUO6vkSELfsJDnKSZW0/c5kRAz5muPrMjonfgwUaFyz/4UKBNOQXMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T04:00:57.021068Z","bundle_sha256":"d3c4ae9ea4ca11f686dff1e15ae6fc8e255c4578f7af6caccde537f763bab32a"}}