{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OX3CISWEFOK5N6LWBES6HVN6PS","short_pith_number":"pith:OX3CISWE","canonical_record":{"source":{"id":"2303.00750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T18:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"8061ff8fe8c720f28e0ac97936b5a18d10b7f3328b16d22d64633b2ee5eda56b","abstract_canon_sha256":"612de881607a2fd0553ed0c2741043beca6e745e5bc5a6120832a8bc911782c0"},"schema_version":"1.0"},"canonical_sha256":"75f6244ac42b95d6f9760925e3d5be7c8a8330bb5900267b3a29741d267370cd","source":{"kind":"arxiv","id":"2303.00750","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00750","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00750v1","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00750","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"pith_short_12","alias_value":"OX3CISWEFOK5","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"pith_short_16","alias_value":"OX3CISWEFOK5N6LW","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"pith_short_8","alias_value":"OX3CISWE","created_at":"2026-07-05T05:47:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OX3CISWEFOK5N6LWBES6HVN6PS","target":"record","payload":{"canonical_record":{"source":{"id":"2303.00750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T18:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"8061ff8fe8c720f28e0ac97936b5a18d10b7f3328b16d22d64633b2ee5eda56b","abstract_canon_sha256":"612de881607a2fd0553ed0c2741043beca6e745e5bc5a6120832a8bc911782c0"},"schema_version":"1.0"},"canonical_sha256":"75f6244ac42b95d6f9760925e3d5be7c8a8330bb5900267b3a29741d267370cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:12.339716Z","signature_b64":"OOTmPsvY6NOgfWaBLCe/DiZtIUCyfSQ7y4jzNhmsFpirE+7sVqwlEEE3ggvhyAUeVRIfzC50JIn91fOrgRERAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75f6244ac42b95d6f9760925e3d5be7c8a8330bb5900267b3a29741d267370cd","last_reissued_at":"2026-07-05T05:47:12.339224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:12.339224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.00750","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":"2026-07-05T05:47:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S1rAE3sVAnjVGZ2a+cdU+ezZB2zZL1tO1EbmEabltuJlbpL+I9p9omr2l3B7PjqMVxpT4bGfzwvAYsdik+7yBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:12:15.555116Z"},"content_sha256":"96bf37030819671b4dea8cdb28f5cadaa7cb426259e834e36ae95ef976d22188","schema_version":"1.0","event_id":"sha256:96bf37030819671b4dea8cdb28f5cadaa7cb426259e834e36ae95ef976d22188"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OX3CISWEFOK5N6LWBES6HVN6PS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StraIT: Non-autoregressive Generation with Stratified Image Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Zhang, Huiwen Chang, Jiaya Jia, Shengju Qian, Yuanzhen Li, Zizhao Zhang","submitted_at":"2023-03-01T18:59:33Z","abstract_excerpt":"We propose Stratified Image Transformer(StraIT), a pure non-autoregressive(NAR) generative model that demonstrates superiority in high-quality image synthesis over existing autoregressive(AR) and diffusion models(DMs). In contrast to the under-exploitation of visual characteristics in existing vision tokenizer, we leverage the hierarchical nature of images to encode visual tokens into stratified levels with emergent properties. Through the proposed image stratification that obtains an interlinked token pair, we alleviate the modeling difficulty and lift the generative power of NAR models. Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00750","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/2303.00750/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":"2026-07-05T05:47:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NfJdEVp7wcETHTmzI/zdd9ojhf/0sOEKaE3N0tOxprWo8PuWMzfeYddebgYBqdpzBu4HuseOto3P6qJz4vp5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:12:15.555528Z"},"content_sha256":"d6aea32cc44d7df4818cab7fa3cbb5b48706b6aa31f1f326c2e5849175187b37","schema_version":"1.0","event_id":"sha256:d6aea32cc44d7df4818cab7fa3cbb5b48706b6aa31f1f326c2e5849175187b37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OX3CISWEFOK5N6LWBES6HVN6PS/bundle.json","state_url":"https://pith.science/pith/OX3CISWEFOK5N6LWBES6HVN6PS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OX3CISWEFOK5N6LWBES6HVN6PS/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":"2026-07-08T19:12:15Z","links":{"resolver":"https://pith.science/pith/OX3CISWEFOK5N6LWBES6HVN6PS","bundle":"https://pith.science/pith/OX3CISWEFOK5N6LWBES6HVN6PS/bundle.json","state":"https://pith.science/pith/OX3CISWEFOK5N6LWBES6HVN6PS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OX3CISWEFOK5N6LWBES6HVN6PS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OX3CISWEFOK5N6LWBES6HVN6PS","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":"612de881607a2fd0553ed0c2741043beca6e745e5bc5a6120832a8bc911782c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T18:59:33Z","title_canon_sha256":"8061ff8fe8c720f28e0ac97936b5a18d10b7f3328b16d22d64633b2ee5eda56b"},"schema_version":"1.0","source":{"id":"2303.00750","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00750","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00750v1","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00750","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"pith_short_12","alias_value":"OX3CISWEFOK5","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"pith_short_16","alias_value":"OX3CISWEFOK5N6LW","created_at":"2026-07-05T05:47:12Z"},{"alias_kind":"pith_short_8","alias_value":"OX3CISWE","created_at":"2026-07-05T05:47:12Z"}],"graph_snapshots":[{"event_id":"sha256:d6aea32cc44d7df4818cab7fa3cbb5b48706b6aa31f1f326c2e5849175187b37","target":"graph","created_at":"2026-07-05T05:47:12Z","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/2303.00750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Stratified Image Transformer(StraIT), a pure non-autoregressive(NAR) generative model that demonstrates superiority in high-quality image synthesis over existing autoregressive(AR) and diffusion models(DMs). In contrast to the under-exploitation of visual characteristics in existing vision tokenizer, we leverage the hierarchical nature of images to encode visual tokens into stratified levels with emergent properties. Through the proposed image stratification that obtains an interlinked token pair, we alleviate the modeling difficulty and lift the generative power of NAR models. Our ","authors_text":"Han Zhang, Huiwen Chang, Jiaya Jia, Shengju Qian, Yuanzhen Li, Zizhao Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T18:59:33Z","title":"StraIT: Non-autoregressive Generation with Stratified Image Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00750","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":"sha256:96bf37030819671b4dea8cdb28f5cadaa7cb426259e834e36ae95ef976d22188","target":"record","created_at":"2026-07-05T05:47:12Z","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":"612de881607a2fd0553ed0c2741043beca6e745e5bc5a6120832a8bc911782c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T18:59:33Z","title_canon_sha256":"8061ff8fe8c720f28e0ac97936b5a18d10b7f3328b16d22d64633b2ee5eda56b"},"schema_version":"1.0","source":{"id":"2303.00750","kind":"arxiv","version":1}},"canonical_sha256":"75f6244ac42b95d6f9760925e3d5be7c8a8330bb5900267b3a29741d267370cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75f6244ac42b95d6f9760925e3d5be7c8a8330bb5900267b3a29741d267370cd","first_computed_at":"2026-07-05T05:47:12.339224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:12.339224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OOTmPsvY6NOgfWaBLCe/DiZtIUCyfSQ7y4jzNhmsFpirE+7sVqwlEEE3ggvhyAUeVRIfzC50JIn91fOrgRERAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:12.339716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.00750","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96bf37030819671b4dea8cdb28f5cadaa7cb426259e834e36ae95ef976d22188","sha256:d6aea32cc44d7df4818cab7fa3cbb5b48706b6aa31f1f326c2e5849175187b37"],"state_sha256":"8991de264121c07165f4ebb7f7990d774f4759fda7cadc067b0b3c894c4eb991"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u6mjEa47B842Ua58dSpffesd/eggwDfcdiNC73LPR2h2cFIwrIy4PW80GKLv/S0WCPEeQ1BgVO/irpN/0K7oDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:12:15.557562Z","bundle_sha256":"aade84dc95278df718b9102cad9cf3f08714c5ce732a9dcecee7c0b00a954129"}}