{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OFYD3BQBKHIJEVPBASA4I6MSI5","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":"227b4172302db37f827776511187d1dac804c004457a223bd689b7822d1b1ecf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-05T17:56:03Z","title_canon_sha256":"f6451f9109d333df08946c12c9ef17e3e2e5d8a210a01bbc178f367d63058032"},"schema_version":"1.0","source":{"id":"2103.03841","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03841","created_at":"2026-07-05T02:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03841v1","created_at":"2026-07-05T02:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03841","created_at":"2026-07-05T02:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"OFYD3BQBKHIJ","created_at":"2026-07-05T02:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"OFYD3BQBKHIJEVPB","created_at":"2026-07-05T02:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"OFYD3BQB","created_at":"2026-07-05T02:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:4c7d841f05df6723cfd845e0fb52c54165810b4ad6034d1b52f0b76ebe493011","target":"graph","created_at":"2026-07-05T02:20:40Z","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/2103.03841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The high dimensionality of images presents architecture and sampling-efficiency challenges for likelihood-based generative models. Previous approaches such as VQ-VAE use deep autoencoders to obtain compact representations, which are more practical as inputs for likelihood-based models. We present an alternative approach, inspired by common image compression methods like JPEG, and convert images to quantized discrete cosine transform (DCT) blocks, which are represented sparsely as a sequence of DCT channel, spatial location, and DCT coefficient triples. We propose a Transformer-based autoregres","authors_text":"Charlie Nash, Jacob Menick, Peter W. Battaglia, Sander Dieleman","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-05T17:56:03Z","title":"Generating Images with Sparse Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03841","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":"sha256:44c7cebf379c6d496be88e39259a2b28f33252bd3a70435b16ee6947d90a1cac","target":"record","created_at":"2026-07-05T02:20:40Z","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":"227b4172302db37f827776511187d1dac804c004457a223bd689b7822d1b1ecf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-05T17:56:03Z","title_canon_sha256":"f6451f9109d333df08946c12c9ef17e3e2e5d8a210a01bbc178f367d63058032"},"schema_version":"1.0","source":{"id":"2103.03841","kind":"arxiv","version":1}},"canonical_sha256":"71703d860151d09255e10481c4799247408b2f581a2ab7041c3411072b03fbe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71703d860151d09255e10481c4799247408b2f581a2ab7041c3411072b03fbe0","first_computed_at":"2026-07-05T02:20:40.359673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:40.359673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D0z9lzC+vpJxEUAVdQQYPlDPK+FiNvLl7hmErfceY9rkPUBN9DmbnYxem2wVVmmuPXwu+LU41x/H1u4LURxFCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:40.360156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.03841","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44c7cebf379c6d496be88e39259a2b28f33252bd3a70435b16ee6947d90a1cac","sha256:4c7d841f05df6723cfd845e0fb52c54165810b4ad6034d1b52f0b76ebe493011"],"state_sha256":"a50dacb608abc9951261f362096537eacb3febc95c885f54d92e64287b588e21"}