{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z2MP5YMOOMMCNLPENPO5FLA3B3","short_pith_number":"pith:Z2MP5YMO","schema_version":"1.0","canonical_sha256":"ce98fee18e731826ade46bddd2ac1b0eda0a0d3b055c19c88185d54ba5bfa923","source":{"kind":"arxiv","id":"2411.00776","version":1},"attestation_state":"computed","paper":{"title":"Randomized Autoregressive Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ju He, Liang-Chieh Chen, Qihang Yu, Xiaohui Shen, Xueqing Deng","submitted_at":"2024-11-01T17:59:58Z","abstract_excerpt":"This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The proposed RAR is simple: during a standard autoregressive training process with a next-token prediction objective, the input sequence-typically ordered in raster form-is randomly permuted into different factorization orders with a probability r, where r starts at 1 and linearly decays to 0 over the course of training. This annealing training strategy enables the m"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.00776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"dc475e0d8fec271b89a184a44c801533eee2d5244ce3c53067d4434ea30db373","abstract_canon_sha256":"c06a5bbc944d1720bdacdd11643b9b6904a5365021bc509967c234abd42ebc58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:48.101658Z","signature_b64":"GtJWu8IQln3c54jFummjNGSAfvZ8x35siafqPYHNfNXP0ME/elYpujnrn8QVP9nH30TBCtIdMrhwatjmddiUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce98fee18e731826ade46bddd2ac1b0eda0a0d3b055c19c88185d54ba5bfa923","last_reissued_at":"2026-07-05T09:29:48.101274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:48.101274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Autoregressive Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ju He, Liang-Chieh Chen, Qihang Yu, Xiaohui Shen, Xueqing Deng","submitted_at":"2024-11-01T17:59:58Z","abstract_excerpt":"This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The proposed RAR is simple: during a standard autoregressive training process with a next-token prediction objective, the input sequence-typically ordered in raster form-is randomly permuted into different factorization orders with a probability r, where r starts at 1 and linearly decays to 0 over the course of training. This annealing training strategy enables the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00776","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/2411.00776/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.00776","created_at":"2026-07-05T09:29:48.101337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00776v1","created_at":"2026-07-05T09:29:48.101337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00776","created_at":"2026-07-05T09:29:48.101337+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2MP5YMOOMMC","created_at":"2026-07-05T09:29:48.101337+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2MP5YMOOMMCNLPE","created_at":"2026-07-05T09:29:48.101337+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2MP5YMO","created_at":"2026-07-05T09:29:48.101337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25548","citing_title":"Concept Removal for Frontier Image Generative Models","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07185","citing_title":"AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06137","citing_title":"Autoregressive Visual Generation Needs a Prologue","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31991","citing_title":"Amplifying Membership Signal Through Chained Regeneration","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17069","citing_title":"Distilling Specialized Orders for Visual Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2505.05472","citing_title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13179","citing_title":"Does Engram Do Memory Retrieval in Autoregressive Image Generation?","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06137","citing_title":"Autoregressive Visual Generation Needs a Prologue","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2MP5YMOOMMCNLPENPO5FLA3B3","json":"https://pith.science/pith/Z2MP5YMOOMMCNLPENPO5FLA3B3.json","graph_json":"https://pith.science/api/pith-number/Z2MP5YMOOMMCNLPENPO5FLA3B3/graph.json","events_json":"https://pith.science/api/pith-number/Z2MP5YMOOMMCNLPENPO5FLA3B3/events.json","paper":"https://pith.science/paper/Z2MP5YMO"},"agent_actions":{"view_html":"https://pith.science/pith/Z2MP5YMOOMMCNLPENPO5FLA3B3","download_json":"https://pith.science/pith/Z2MP5YMOOMMCNLPENPO5FLA3B3.json","view_paper":"https://pith.science/paper/Z2MP5YMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00776&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2MP5YMOOMMCNLPENPO5FLA3B3/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2MP5YMOOMMCNLPENPO5FLA3B3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2MP5YMOOMMCNLPENPO5FLA3B3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2MP5YMOOMMCNLPENPO5FLA3B3/action/storage_attestation","attest_author":"https://pith.science/pith/Z2MP5YMOOMMCNLPENPO5FLA3B3/action/author_attestation","sign_citation":"https://pith.science/pith/Z2MP5YMOOMMCNLPENPO5FLA3B3/action/citation_signature","submit_replication":"https://pith.science/pith/Z2MP5YMOOMMCNLPENPO5FLA3B3/action/replication_record"}},"created_at":"2026-07-05T09:29:48.101337+00:00","updated_at":"2026-07-05T09:29:48.101337+00:00"}