{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XSKNLCCVLT4XV5FCCPJPVJ6ZZA","short_pith_number":"pith:XSKNLCCV","canonical_record":{"source":{"id":"2405.21048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:41:11Z","cross_cats_sorted":[],"title_canon_sha256":"7f821335e5b115f63a74e3a1b48d8eb401f9abacdbc262de07182fae8e1e7a13","abstract_canon_sha256":"1b4b605c9f32a3c7a72f6226b8b58126afbd41b919d7fa06b491f23b9de6ba92"},"schema_version":"1.0"},"canonical_sha256":"bc94d588555cf97af4a213d2faa7d9c8137951d6f7e7d79210d933a7f996ecfd","source":{"kind":"arxiv","id":"2405.21048","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.21048","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"arxiv_version","alias_value":"2405.21048v1","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.21048","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_12","alias_value":"XSKNLCCVLT4X","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_16","alias_value":"XSKNLCCVLT4XV5FC","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_8","alias_value":"XSKNLCCV","created_at":"2026-07-05T08:25:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XSKNLCCVLT4XV5FCCPJPVJ6ZZA","target":"record","payload":{"canonical_record":{"source":{"id":"2405.21048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:41:11Z","cross_cats_sorted":[],"title_canon_sha256":"7f821335e5b115f63a74e3a1b48d8eb401f9abacdbc262de07182fae8e1e7a13","abstract_canon_sha256":"1b4b605c9f32a3c7a72f6226b8b58126afbd41b919d7fa06b491f23b9de6ba92"},"schema_version":"1.0"},"canonical_sha256":"bc94d588555cf97af4a213d2faa7d9c8137951d6f7e7d79210d933a7f996ecfd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:45.342032Z","signature_b64":"Xgxi75VVSNjo8GOCKjIro0QpPiKXfo+zevGkvcU4N6wLICU5Wv7XpvOHisH+SpzwkdkzP6azr0Lnc16TqK35DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc94d588555cf97af4a213d2faa7d9c8137951d6f7e7d79210d933a7f996ecfd","last_reissued_at":"2026-07-05T08:25:45.341503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:45.341503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.21048","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dWe2/a1hNOdhabYzJr/l2ozfLSIlKoJmTX3sH0wSHusZpAcKsap974OWVSYVfMj5SMAvbSVdoblDC/F/quR1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:27:42.723840Z"},"content_sha256":"1d8d7240c5c4e63a6ec74e45189b506b10060e4d56be7e65b21eaf0ab1fbde77","schema_version":"1.0","event_id":"sha256:1d8d7240c5c4e63a6ec74e45189b506b10060e4d56be7e65b21eaf0ab1fbde77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XSKNLCCVLT4XV5FCCPJPVJ6ZZA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiatao Gu, Joshua M. Susskind, Navdeep Jaitly, Shuangfei Zhai, Ying Shen, Yizhe Zhang","submitted_at":"2024-05-31T17:41:11Z","abstract_excerpt":"Diffusion models have emerged as a powerful tool for generating high-quality images from textual descriptions. Despite their successes, these models often exhibit limited diversity in the sampled images, particularly when sampling with a high classifier-free guidance weight. To address this issue, we present Kaleido, a novel approach that enhances the diversity of samples by incorporating autoregressive latent priors. Kaleido integrates an autoregressive language model that encodes the original caption and generates latent variables, serving as abstract and intermediary representations for gui"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.21048","kind":"arxiv","version":1},"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/2405.21048/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":"2026-07-05T08:25:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NL2X8jp1X7Pd3hWfljzuByRCRXNisbjxViZHlfLbnRn9h28bM+BYgoLnSf1kVuyggq4pcbARiVcacataD4NEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:27:42.724854Z"},"content_sha256":"c30b14e3db35f6a0e2c847522062bcf54f9301ac6209efb8d219d58938e250f0","schema_version":"1.0","event_id":"sha256:c30b14e3db35f6a0e2c847522062bcf54f9301ac6209efb8d219d58938e250f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XSKNLCCVLT4XV5FCCPJPVJ6ZZA/bundle.json","state_url":"https://pith.science/pith/XSKNLCCVLT4XV5FCCPJPVJ6ZZA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XSKNLCCVLT4XV5FCCPJPVJ6ZZA/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":"2026-08-12T12:27:42Z","links":{"resolver":"https://pith.science/pith/XSKNLCCVLT4XV5FCCPJPVJ6ZZA","bundle":"https://pith.science/pith/XSKNLCCVLT4XV5FCCPJPVJ6ZZA/bundle.json","state":"https://pith.science/pith/XSKNLCCVLT4XV5FCCPJPVJ6ZZA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XSKNLCCVLT4XV5FCCPJPVJ6ZZA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XSKNLCCVLT4XV5FCCPJPVJ6ZZA","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":"1b4b605c9f32a3c7a72f6226b8b58126afbd41b919d7fa06b491f23b9de6ba92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:41:11Z","title_canon_sha256":"7f821335e5b115f63a74e3a1b48d8eb401f9abacdbc262de07182fae8e1e7a13"},"schema_version":"1.0","source":{"id":"2405.21048","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.21048","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"arxiv_version","alias_value":"2405.21048v1","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.21048","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_12","alias_value":"XSKNLCCVLT4X","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_16","alias_value":"XSKNLCCVLT4XV5FC","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_8","alias_value":"XSKNLCCV","created_at":"2026-07-05T08:25:45Z"}],"graph_snapshots":[{"event_id":"sha256:c30b14e3db35f6a0e2c847522062bcf54f9301ac6209efb8d219d58938e250f0","target":"graph","created_at":"2026-07-05T08:25:45Z","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/2405.21048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have emerged as a powerful tool for generating high-quality images from textual descriptions. Despite their successes, these models often exhibit limited diversity in the sampled images, particularly when sampling with a high classifier-free guidance weight. To address this issue, we present Kaleido, a novel approach that enhances the diversity of samples by incorporating autoregressive latent priors. Kaleido integrates an autoregressive language model that encodes the original caption and generates latent variables, serving as abstract and intermediary representations for gui","authors_text":"Jiatao Gu, Joshua M. Susskind, Navdeep Jaitly, Shuangfei Zhai, Ying Shen, Yizhe Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:41:11Z","title":"Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.21048","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":"sha256:1d8d7240c5c4e63a6ec74e45189b506b10060e4d56be7e65b21eaf0ab1fbde77","target":"record","created_at":"2026-07-05T08:25:45Z","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":"1b4b605c9f32a3c7a72f6226b8b58126afbd41b919d7fa06b491f23b9de6ba92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:41:11Z","title_canon_sha256":"7f821335e5b115f63a74e3a1b48d8eb401f9abacdbc262de07182fae8e1e7a13"},"schema_version":"1.0","source":{"id":"2405.21048","kind":"arxiv","version":1}},"canonical_sha256":"bc94d588555cf97af4a213d2faa7d9c8137951d6f7e7d79210d933a7f996ecfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc94d588555cf97af4a213d2faa7d9c8137951d6f7e7d79210d933a7f996ecfd","first_computed_at":"2026-07-05T08:25:45.341503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:45.341503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xgxi75VVSNjo8GOCKjIro0QpPiKXfo+zevGkvcU4N6wLICU5Wv7XpvOHisH+SpzwkdkzP6azr0Lnc16TqK35DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:45.342032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.21048","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d8d7240c5c4e63a6ec74e45189b506b10060e4d56be7e65b21eaf0ab1fbde77","sha256:c30b14e3db35f6a0e2c847522062bcf54f9301ac6209efb8d219d58938e250f0"],"state_sha256":"da14ecc7c28a27b7e944f91aaef2bdf741782171febf9873133d4c21bac17615"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UqLwQnZJj/bkKwE1kduMnTMbnxtrCpFM3bt6lkb6g9giJRYjlW5tAUqxtqX05QySVWgqBtW2PvUal+P5ZENSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:27:42.743652Z","bundle_sha256":"57c4893102e6241d770d173f2d36fea37488a1e1136d240b591b47c1cbadec6b"}}