{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GGAQ7QBWW4IAB4J6LSGROYRUDS","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":"ba75580569f6e1ced1bfaf61e236ea18c6d1bbb71ef0a77ec715631e8e38e53c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T18:59:08Z","title_canon_sha256":"3ca8104159da1e7c88ec8c5d097c87c9d4234f81a3a3ec50bdac3675ec744b8c"},"schema_version":"1.0","source":{"id":"2502.20388","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20388","created_at":"2026-07-05T10:36:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20388v2","created_at":"2026-07-05T10:36:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20388","created_at":"2026-07-05T10:36:36Z"},{"alias_kind":"pith_short_12","alias_value":"GGAQ7QBWW4IA","created_at":"2026-07-05T10:36:36Z"},{"alias_kind":"pith_short_16","alias_value":"GGAQ7QBWW4IAB4J6","created_at":"2026-07-05T10:36:36Z"},{"alias_kind":"pith_short_8","alias_value":"GGAQ7QBW","created_at":"2026-07-05T10:36:36Z"}],"graph_snapshots":[{"event_id":"sha256:2dc680e946539f87aa911376b0809bfc2c7686efbf97a1902b97040e6778bcbb","target":"graph","created_at":"2026-07-05T10:36:36Z","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/2502.20388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive (AR) modeling, known for its next-token prediction paradigm, underpins state-of-the-art language and visual generative models. Traditionally, a ``token'' is treated as the smallest prediction unit, often a discrete symbol in language or a quantized patch in vision. However, the optimal token definition for 2D image structures remains an open question. Moreover, AR models suffer from exposure bias, where teacher forcing during training leads to error accumulation at inference. In this paper, we propose xAR, a generalized AR framework that extends the notion of a token to an entit","authors_text":"Alan Yuille, Ju He, Liang-Chieh Chen, Qihang Yu, Sucheng Ren, Xiaohui Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T18:59:08Z","title":"Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20388","kind":"arxiv","version":2},"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":"sha256:09c06c66ed6022d5aeb3efe4664af0637190cb3ea82614380142c9d48dabeff0","target":"record","created_at":"2026-07-05T10:36:36Z","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":"ba75580569f6e1ced1bfaf61e236ea18c6d1bbb71ef0a77ec715631e8e38e53c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T18:59:08Z","title_canon_sha256":"3ca8104159da1e7c88ec8c5d097c87c9d4234f81a3a3ec50bdac3675ec744b8c"},"schema_version":"1.0","source":{"id":"2502.20388","kind":"arxiv","version":2}},"canonical_sha256":"31810fc036b71000f13e5c8d1762341ca9dbaa9824afc6bdc22ed77604535e11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31810fc036b71000f13e5c8d1762341ca9dbaa9824afc6bdc22ed77604535e11","first_computed_at":"2026-07-05T10:36:36.927637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:36.927637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ADhJ0XNyu1mH6coDGtt1dxTF7uf9LBUtLd/6oU5CjtpctYD4SNdOQ3vqQDsJByQsXHoyXu108/2MXmVjQVTUAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:36.928268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20388","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09c06c66ed6022d5aeb3efe4664af0637190cb3ea82614380142c9d48dabeff0","sha256:2dc680e946539f87aa911376b0809bfc2c7686efbf97a1902b97040e6778bcbb"],"state_sha256":"e6a3f52c82cb4322ef5609cc4f5e54e102e6f1c4b6aafc8edd4a813d2d681752"}