{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7OM5ZJNWDRB4IBZLSGXFMZDSNL","short_pith_number":"pith:7OM5ZJNW","canonical_record":{"source":{"id":"2606.27147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T15:18:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5328fdfdaf6d0d548a8d1bbfbb3e5a847589fd645e4d6280cf27155c3bd968d","abstract_canon_sha256":"70d1d4712191f3d3aae1d3d2fcf8d6ce06677abf785b785f205c10bf4e83c56f"},"schema_version":"1.0"},"canonical_sha256":"fb99dca5b61c43c4072b91ae5664726ad83b6b74bc5b0b708ec7c88c27ea917a","source":{"kind":"arxiv","id":"2606.27147","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27147","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27147v1","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27147","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"pith_short_12","alias_value":"7OM5ZJNWDRB4","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"pith_short_16","alias_value":"7OM5ZJNWDRB4IBZL","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"pith_short_8","alias_value":"7OM5ZJNW","created_at":"2026-06-26T01:16:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7OM5ZJNWDRB4IBZLSGXFMZDSNL","target":"record","payload":{"canonical_record":{"source":{"id":"2606.27147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T15:18:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5328fdfdaf6d0d548a8d1bbfbb3e5a847589fd645e4d6280cf27155c3bd968d","abstract_canon_sha256":"70d1d4712191f3d3aae1d3d2fcf8d6ce06677abf785b785f205c10bf4e83c56f"},"schema_version":"1.0"},"canonical_sha256":"fb99dca5b61c43c4072b91ae5664726ad83b6b74bc5b0b708ec7c88c27ea917a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:11.520241Z","signature_b64":"04RhWVcSe6xU5GdRZwvGl3E8jDtOu0EglDce0DEUWEzC1mseNTX4IZsLZQm0WLwCM9+NeD8M3hF2Skw4V4SdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb99dca5b61c43c4072b91ae5664726ad83b6b74bc5b0b708ec7c88c27ea917a","last_reissued_at":"2026-06-26T01:16:11.519860Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:11.519860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.27147","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":"2026-06-26T01:16:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"srB+hk3oyQGK6XGkKmvFDzJ72AsU31J/9s81H13cH/0FHoFJIpzDtV0sxCI1b5XQVotNn+SNIQZ570Vc4X22Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:31:09.360644Z"},"content_sha256":"014ab7f9e013ce5918648e62455bd25d9a3431f0bb00ea9918ae3f6674da2afe","schema_version":"1.0","event_id":"sha256:014ab7f9e013ce5918648e62455bd25d9a3431f0bb00ea9918ae3f6674da2afe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7OM5ZJNWDRB4IBZLSGXFMZDSNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jindong Gu, Philip Torr, Yunqi Xue, Zhijiang Li","submitted_at":"2026-06-25T15:18:31Z","abstract_excerpt":"Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebook that maps embeddings to quantized visual patterns. The language-like architecture enables unified multimodal models to effectively capture text conditional information for generation, making them promising for text-to-image tasks. This also raises an interesting question: how safe are the images generated in such an autoregressive way? In this work, we propose iterative self"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27147","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/2606.27147/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":"2026-06-26T01:16:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QMgu81sZ7T9DgEDxVSdpSus4fgNdZyKQ6eo2o858VUD43HCSa4PEkU7FlwrVGjA88KwW6X6e4KS+teS/xJQJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:31:09.361015Z"},"content_sha256":"2be0555dec66a704e30c893962e219f2c5bd1f0ccaaded3aa38dd87419cc9cd2","schema_version":"1.0","event_id":"sha256:2be0555dec66a704e30c893962e219f2c5bd1f0ccaaded3aa38dd87419cc9cd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7OM5ZJNWDRB4IBZLSGXFMZDSNL/bundle.json","state_url":"https://pith.science/pith/7OM5ZJNWDRB4IBZLSGXFMZDSNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7OM5ZJNWDRB4IBZLSGXFMZDSNL/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":"2026-07-04T18:31:09Z","links":{"resolver":"https://pith.science/pith/7OM5ZJNWDRB4IBZLSGXFMZDSNL","bundle":"https://pith.science/pith/7OM5ZJNWDRB4IBZLSGXFMZDSNL/bundle.json","state":"https://pith.science/pith/7OM5ZJNWDRB4IBZLSGXFMZDSNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7OM5ZJNWDRB4IBZLSGXFMZDSNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7OM5ZJNWDRB4IBZLSGXFMZDSNL","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":"70d1d4712191f3d3aae1d3d2fcf8d6ce06677abf785b785f205c10bf4e83c56f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T15:18:31Z","title_canon_sha256":"d5328fdfdaf6d0d548a8d1bbfbb3e5a847589fd645e4d6280cf27155c3bd968d"},"schema_version":"1.0","source":{"id":"2606.27147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27147","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27147v1","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27147","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"pith_short_12","alias_value":"7OM5ZJNWDRB4","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"pith_short_16","alias_value":"7OM5ZJNWDRB4IBZL","created_at":"2026-06-26T01:16:11Z"},{"alias_kind":"pith_short_8","alias_value":"7OM5ZJNW","created_at":"2026-06-26T01:16:11Z"}],"graph_snapshots":[{"event_id":"sha256:2be0555dec66a704e30c893962e219f2c5bd1f0ccaaded3aa38dd87419cc9cd2","target":"graph","created_at":"2026-06-26T01:16:11Z","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/2606.27147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebook that maps embeddings to quantized visual patterns. The language-like architecture enables unified multimodal models to effectively capture text conditional information for generation, making them promising for text-to-image tasks. This also raises an interesting question: how safe are the images generated in such an autoregressive way? In this work, we propose iterative self","authors_text":"Jindong Gu, Philip Torr, Yunqi Xue, Zhijiang Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T15:18:31Z","title":"Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27147","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":"sha256:014ab7f9e013ce5918648e62455bd25d9a3431f0bb00ea9918ae3f6674da2afe","target":"record","created_at":"2026-06-26T01:16:11Z","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":"70d1d4712191f3d3aae1d3d2fcf8d6ce06677abf785b785f205c10bf4e83c56f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T15:18:31Z","title_canon_sha256":"d5328fdfdaf6d0d548a8d1bbfbb3e5a847589fd645e4d6280cf27155c3bd968d"},"schema_version":"1.0","source":{"id":"2606.27147","kind":"arxiv","version":1}},"canonical_sha256":"fb99dca5b61c43c4072b91ae5664726ad83b6b74bc5b0b708ec7c88c27ea917a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb99dca5b61c43c4072b91ae5664726ad83b6b74bc5b0b708ec7c88c27ea917a","first_computed_at":"2026-06-26T01:16:11.519860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:11.519860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"04RhWVcSe6xU5GdRZwvGl3E8jDtOu0EglDce0DEUWEzC1mseNTX4IZsLZQm0WLwCM9+NeD8M3hF2Skw4V4SdDg==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:11.520241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:014ab7f9e013ce5918648e62455bd25d9a3431f0bb00ea9918ae3f6674da2afe","sha256:2be0555dec66a704e30c893962e219f2c5bd1f0ccaaded3aa38dd87419cc9cd2"],"state_sha256":"7ea32e833abf317183f24bb43b77060c880f241df481b7d11d4b335a9e40484d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"05AfZTqvCpHFA1UI9ZGqK6fqKThJ6Ve3+/DfWgFE0DVCxzqos+6w3eat2tubsv69+T9jZNwvo9o4MObjJShUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T18:31:09.363166Z","bundle_sha256":"79caeffc3c15e41cb1fe0c5143ebba3a160c8c26c84f4d56c598501300135dd3"}}