{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PYGZTKHM7TAOW2T3RHHTJPE3OM","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":"cf57bcebd7dab94d95f56e24d1bff9e3c8e075d209b9b55399320fc06272cdb9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T18:59:46Z","title_canon_sha256":"56224aade1924f001d739b95d040cba4b57f9c1dcf8776e944d3614348815da3"},"schema_version":"1.0","source":{"id":"2111.14822","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.14822","created_at":"2026-07-05T04:01:44Z"},{"alias_kind":"arxiv_version","alias_value":"2111.14822v3","created_at":"2026-07-05T04:01:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14822","created_at":"2026-07-05T04:01:44Z"},{"alias_kind":"pith_short_12","alias_value":"PYGZTKHM7TAO","created_at":"2026-07-05T04:01:44Z"},{"alias_kind":"pith_short_16","alias_value":"PYGZTKHM7TAOW2T3","created_at":"2026-07-05T04:01:44Z"},{"alias_kind":"pith_short_8","alias_value":"PYGZTKHM","created_at":"2026-07-05T04:01:44Z"}],"graph_snapshots":[{"event_id":"sha256:5342083f20cb7eb904a7de6dcab183e308b7fa055f7a391d086616e116e5e44b","target":"graph","created_at":"2026-07-05T04:01:44Z","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/2111.14822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent space is modeled by a conditional variant of the recently developed Denoising Diffusion Probabilistic Model (DDPM). We find that this latent-space method is well-suited for text-to-image generation tasks because it not only eliminates the unidirectional bias with existing methods but also allows us to incorporate a mask-and-replace diffusion strategy to avoid the accumulation of errors, which is a serious problem w","authors_text":"Baining Guo, Bo Zhang, Dong Chen, Dongdong Chen, Fang Wen, Jianmin Bao, Lu Yuan, Shuyang Gu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T18:59:46Z","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14822","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":"sha256:561f15241602479a373f20a4e204cf937b45071b53fbd4881437aab1242bf40d","target":"record","created_at":"2026-07-05T04:01:44Z","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":"cf57bcebd7dab94d95f56e24d1bff9e3c8e075d209b9b55399320fc06272cdb9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T18:59:46Z","title_canon_sha256":"56224aade1924f001d739b95d040cba4b57f9c1dcf8776e944d3614348815da3"},"schema_version":"1.0","source":{"id":"2111.14822","kind":"arxiv","version":3}},"canonical_sha256":"7e0d99a8ecfcc0eb6a7b89cf34bc9b7322388ec7ce57e972c195b60472001e24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e0d99a8ecfcc0eb6a7b89cf34bc9b7322388ec7ce57e972c195b60472001e24","first_computed_at":"2026-07-05T04:01:44.893635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:44.893635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kwwfcwyrb55sD79H/XrGXNfwUuvGDdIQRGMsep3A8u2WLWZWeg8cILfxXW13MG2QL2tOdiVg00e9NuksQ+apBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:44.894113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.14822","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:561f15241602479a373f20a4e204cf937b45071b53fbd4881437aab1242bf40d","sha256:5342083f20cb7eb904a7de6dcab183e308b7fa055f7a391d086616e116e5e44b"],"state_sha256":"74f8b346d5ca6ca3ae438d5066bab426ddeecf1e2eb2715a0fe8a279ce6dac75"}