{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2SMLEFHBNTL64XXX6MTNCDG7ET","short_pith_number":"pith:2SMLEFHB","canonical_record":{"source":{"id":"2412.15321","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"482a57ff2539586d3f2b97375b2d06ab5e1b43421f2e2bce98900dd3a5731270","abstract_canon_sha256":"d3f64f24d2a653d0fe56c22abe4c2682542cb89bf4bf6a2a3c84fc6a6476b4bc"},"schema_version":"1.0"},"canonical_sha256":"d498b214e16cd7ee5ef7f326d10cdf24cd2a73b07e466017b9662519a8fd54a1","source":{"kind":"arxiv","id":"2412.15321","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15321","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15321v3","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15321","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"2SMLEFHBNTL6","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"2SMLEFHBNTL64XXX","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"2SMLEFHB","created_at":"2026-07-05T10:34:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2SMLEFHBNTL64XXX6MTNCDG7ET","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15321","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"482a57ff2539586d3f2b97375b2d06ab5e1b43421f2e2bce98900dd3a5731270","abstract_canon_sha256":"d3f64f24d2a653d0fe56c22abe4c2682542cb89bf4bf6a2a3c84fc6a6476b4bc"},"schema_version":"1.0"},"canonical_sha256":"d498b214e16cd7ee5ef7f326d10cdf24cd2a73b07e466017b9662519a8fd54a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:13.853778Z","signature_b64":"CdcluG738q6n5rSVdNVtlMYrx9uxLEJnBgmvXFpDxRD3fvp3A8Vfo5CO+HbR+Pqdo3C5/4uYaqtdw0I2NRcyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d498b214e16cd7ee5ef7f326d10cdf24cd2a73b07e466017b9662519a8fd54a1","last_reissued_at":"2026-07-05T10:34:13.853218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:13.853218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15321","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Anz8RQCtxuA/LtEt9JE+kpyPrFmRlv+oKF+M9/rhieQvzAkWNNjZ9fM8SlaGpE4JcFVBPYkXD/bXmS/ssVW2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:41:52.245230Z"},"content_sha256":"b6e9be818cea1052a44c8660f79c822b8e4344a0fe0056cd508675c32292829c","schema_version":"1.0","event_id":"sha256:b6e9be818cea1052a44c8660f79c822b8e4344a0fe0056cd508675c32292829c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2SMLEFHBNTL64XXX6MTNCDG7ET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Next Patch Prediction for Autoregressive Visual Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Lin, Bin Zhu, Francis E. H. Tay, Harry Yang, Liuhan Chen, Li Yuan, Peng Jin, Ser-Nam Lim, Shuo Yang, Yatian Pang, Zhenyu Tang","submitted_at":"2024-12-19T18:59:36Z","abstract_excerpt":"Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision tasks. Pioneering works introduce NTP to autoregressive visual generation tasks. In this work, we rethink the NTP for autoregressive image generation and extend it to a novel Next Patch Prediction (NPP) paradigm. Our key idea is to group and aggregate image tokens into patch tokens with higher information density. By using patch tokens as a more compact input sequence, the autoregressive model is trained to predict the n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15321","kind":"arxiv","version":3},"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/2412.15321/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":"2026-07-05T10:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FiNs3SHztfg0N5Lgy0L7f1W1UQ6FVrulSyM6e+/mLYdfKwadnLuNK8oX1DNIXE5xLrGrZMDE2bQLeoCXWwWdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:41:52.245719Z"},"content_sha256":"f5ad48d08e05f7abaa12e63f2c3f39fe84e9dc3c861589b3d1405ae0dc8b5431","schema_version":"1.0","event_id":"sha256:f5ad48d08e05f7abaa12e63f2c3f39fe84e9dc3c861589b3d1405ae0dc8b5431"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2SMLEFHBNTL64XXX6MTNCDG7ET/bundle.json","state_url":"https://pith.science/pith/2SMLEFHBNTL64XXX6MTNCDG7ET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2SMLEFHBNTL64XXX6MTNCDG7ET/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":"2026-08-10T02:41:52Z","links":{"resolver":"https://pith.science/pith/2SMLEFHBNTL64XXX6MTNCDG7ET","bundle":"https://pith.science/pith/2SMLEFHBNTL64XXX6MTNCDG7ET/bundle.json","state":"https://pith.science/pith/2SMLEFHBNTL64XXX6MTNCDG7ET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2SMLEFHBNTL64XXX6MTNCDG7ET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2SMLEFHBNTL64XXX6MTNCDG7ET","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":"d3f64f24d2a653d0fe56c22abe4c2682542cb89bf4bf6a2a3c84fc6a6476b4bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:59:36Z","title_canon_sha256":"482a57ff2539586d3f2b97375b2d06ab5e1b43421f2e2bce98900dd3a5731270"},"schema_version":"1.0","source":{"id":"2412.15321","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15321","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15321v3","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15321","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"2SMLEFHBNTL6","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"2SMLEFHBNTL64XXX","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"2SMLEFHB","created_at":"2026-07-05T10:34:13Z"}],"graph_snapshots":[{"event_id":"sha256:f5ad48d08e05f7abaa12e63f2c3f39fe84e9dc3c861589b3d1405ae0dc8b5431","target":"graph","created_at":"2026-07-05T10:34:13Z","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/2412.15321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision tasks. Pioneering works introduce NTP to autoregressive visual generation tasks. In this work, we rethink the NTP for autoregressive image generation and extend it to a novel Next Patch Prediction (NPP) paradigm. Our key idea is to group and aggregate image tokens into patch tokens with higher information density. By using patch tokens as a more compact input sequence, the autoregressive model is trained to predict the n","authors_text":"Bin Lin, Bin Zhu, Francis E. H. Tay, Harry Yang, Liuhan Chen, Li Yuan, Peng Jin, Ser-Nam Lim, Shuo Yang, Yatian Pang, Zhenyu Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:59:36Z","title":"Next Patch Prediction for Autoregressive Visual Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15321","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:b6e9be818cea1052a44c8660f79c822b8e4344a0fe0056cd508675c32292829c","target":"record","created_at":"2026-07-05T10:34:13Z","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":"d3f64f24d2a653d0fe56c22abe4c2682542cb89bf4bf6a2a3c84fc6a6476b4bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:59:36Z","title_canon_sha256":"482a57ff2539586d3f2b97375b2d06ab5e1b43421f2e2bce98900dd3a5731270"},"schema_version":"1.0","source":{"id":"2412.15321","kind":"arxiv","version":3}},"canonical_sha256":"d498b214e16cd7ee5ef7f326d10cdf24cd2a73b07e466017b9662519a8fd54a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d498b214e16cd7ee5ef7f326d10cdf24cd2a73b07e466017b9662519a8fd54a1","first_computed_at":"2026-07-05T10:34:13.853218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:13.853218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CdcluG738q6n5rSVdNVtlMYrx9uxLEJnBgmvXFpDxRD3fvp3A8Vfo5CO+HbR+Pqdo3C5/4uYaqtdw0I2NRcyAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:13.853778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15321","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6e9be818cea1052a44c8660f79c822b8e4344a0fe0056cd508675c32292829c","sha256:f5ad48d08e05f7abaa12e63f2c3f39fe84e9dc3c861589b3d1405ae0dc8b5431"],"state_sha256":"d79737c8d54b784c49450287454333ef881d3dcc95f50cbb1e6c95f76725399a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y0zklmoftV7+EJwmiQ7pAUrHhPCLQPCR3NdjI8GOJHvpdTqimF8PpIOBIWEA+JQx0jy1naDep3qiI55UX8sHBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:41:52.249464Z","bundle_sha256":"b419321ff798e682e5424aa1916e34d8eb3c1c651af235d2c78e6b1924911b31"}}