{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IAZSHC2CEOVJS5LFPG2ACLALBB","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":"15fed9cdec205952b193885672ba07c81d187e36d77f407888593a2b86873241","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-06T22:49:38Z","title_canon_sha256":"116acf5c8e86ca342bfc6e9b68d7e0a213ef1043dd459235cf3e67ded5134f23"},"schema_version":"1.0","source":{"id":"2401.03321","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03321","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03321v2","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03321","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_12","alias_value":"IAZSHC2CEOVJ","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_16","alias_value":"IAZSHC2CEOVJS5LF","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_8","alias_value":"IAZSHC2C","created_at":"2026-07-05T07:48:51Z"}],"graph_snapshots":[{"event_id":"sha256:770923cf9644fd7580899d1c14390733dc70ef6b46ba434343f3aa44f526103f","target":"graph","created_at":"2026-07-05T07:48:51Z","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/2401.03321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work showed the possibility of building open-vocabulary large language models (LLMs) that directly operate on pixel representations. These models are implemented as autoencoders that reconstruct masked patches of rendered text. However, these pixel-based LLMs are limited to discriminative tasks (e.g., classification) and, similar to BERT, cannot be used to generate text. Therefore, they cannot be used for generative tasks such as free-form question answering. In this work, we introduce PIXAR, the first pixel-based autoregressive LLM that performs text generation. Consisting of only a de","authors_text":"Alessandro Suglia, Antonio Vergari, Xiyang Liao, Yintao Tai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-06T22:49:38Z","title":"PIXAR: Auto-Regressive Language Modeling in Pixel Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03321","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":"sha256:8e2625ccb338cef70993a1427b31190cab2499ea82d69b75635068d34b1b4605","target":"record","created_at":"2026-07-05T07:48:51Z","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":"15fed9cdec205952b193885672ba07c81d187e36d77f407888593a2b86873241","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-06T22:49:38Z","title_canon_sha256":"116acf5c8e86ca342bfc6e9b68d7e0a213ef1043dd459235cf3e67ded5134f23"},"schema_version":"1.0","source":{"id":"2401.03321","kind":"arxiv","version":2}},"canonical_sha256":"4033238b4223aa99756579b4012c0b087ef2121d56f6c9c345a18709683a0609","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4033238b4223aa99756579b4012c0b087ef2121d56f6c9c345a18709683a0609","first_computed_at":"2026-07-05T07:48:51.618690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:51.618690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Uv20MPVeAG7ULAvdzHyIkpom/JLUrkVqkZbulGEx7f3AgtIXk7VVEnvITcU/JWmh+aZ8YbtzhjSA/dGuJ15Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:51.619127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.03321","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e2625ccb338cef70993a1427b31190cab2499ea82d69b75635068d34b1b4605","sha256:770923cf9644fd7580899d1c14390733dc70ef6b46ba434343f3aa44f526103f"],"state_sha256":"d0c017158611504abe56529a556313d6069154478a2bdf40561861f777e5af9c"}