{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L2WGOJ7D7NJSUEVWEN5MDTMSJG","short_pith_number":"pith:L2WGOJ7D","schema_version":"1.0","canonical_sha256":"5eac6727e3fb532a12b6237ac1cd9249bfccdc6eacc83bffb279ec0e9d5a2c62","source":{"kind":"arxiv","id":"2509.26376","version":3},"attestation_state":"computed","paper":{"title":"ScalingAR: Scaling Confidence for Autoregressive Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Disen Lan, Harold Haodong Chen, Harry Yang, Rongjin Guo, Wen-Jie Shu, Xianfeng Wu, Ying-Cong Chen","submitted_at":"2025-09-30T15:08:25Z","abstract_excerpt":"Test-time strategies have shown remarkable success in improving large language models, but their application to next-token prediction (NTP) autoregressive (AR) image generation remains largely underexplored. Existing test-time scaling (TTS) methods for visual autoregressive models (VAR) rely on frequent partial decoding and external reward models, which are inefficient and often ineffective for NTP-based image generation due to the inherent instability of intermediate decoding results. To address these limitations, we propose ScalingAR, a novel test-time scaling framework tailored for NTP-base"},"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":"2509.26376","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-30T15:08:25Z","cross_cats_sorted":[],"title_canon_sha256":"e979f648fccd6de0e34242e3f0b48dcedc03d96a46cd5280a96b34101aa9de8f","abstract_canon_sha256":"672ddf47654e666c4dd067cdb91e77296fcc92ae821f9f8919773b1d5628c5a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:46.457756Z","signature_b64":"2UOfo96pKZ756+EN9Funz992d14WAyFm9WP9tG5v6WaYWGjNazB7dq5r0tFQpve1AC0aPFeW8QjbehON8heOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eac6727e3fb532a12b6237ac1cd9249bfccdc6eacc83bffb279ec0e9d5a2c62","last_reissued_at":"2026-06-25T01:17:46.457219Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:46.457219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScalingAR: Scaling Confidence for Autoregressive Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Disen Lan, Harold Haodong Chen, Harry Yang, Rongjin Guo, Wen-Jie Shu, Xianfeng Wu, Ying-Cong Chen","submitted_at":"2025-09-30T15:08:25Z","abstract_excerpt":"Test-time strategies have shown remarkable success in improving large language models, but their application to next-token prediction (NTP) autoregressive (AR) image generation remains largely underexplored. Existing test-time scaling (TTS) methods for visual autoregressive models (VAR) rely on frequent partial decoding and external reward models, which are inefficient and often ineffective for NTP-based image generation due to the inherent instability of intermediate decoding results. To address these limitations, we propose ScalingAR, a novel test-time scaling framework tailored for NTP-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26376","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/2509.26376/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":"2509.26376","created_at":"2026-06-25T01:17:46.457282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.26376v3","created_at":"2026-06-25T01:17:46.457282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26376","created_at":"2026-06-25T01:17:46.457282+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2WGOJ7D7NJS","created_at":"2026-06-25T01:17:46.457282+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2WGOJ7D7NJSUEVW","created_at":"2026-06-25T01:17:46.457282+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2WGOJ7D","created_at":"2026-06-25T01:17:46.457282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2WGOJ7D7NJSUEVWEN5MDTMSJG","json":"https://pith.science/pith/L2WGOJ7D7NJSUEVWEN5MDTMSJG.json","graph_json":"https://pith.science/api/pith-number/L2WGOJ7D7NJSUEVWEN5MDTMSJG/graph.json","events_json":"https://pith.science/api/pith-number/L2WGOJ7D7NJSUEVWEN5MDTMSJG/events.json","paper":"https://pith.science/paper/L2WGOJ7D"},"agent_actions":{"view_html":"https://pith.science/pith/L2WGOJ7D7NJSUEVWEN5MDTMSJG","download_json":"https://pith.science/pith/L2WGOJ7D7NJSUEVWEN5MDTMSJG.json","view_paper":"https://pith.science/paper/L2WGOJ7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.26376&json=true","fetch_graph":"https://pith.science/api/pith-number/L2WGOJ7D7NJSUEVWEN5MDTMSJG/graph.json","fetch_events":"https://pith.science/api/pith-number/L2WGOJ7D7NJSUEVWEN5MDTMSJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2WGOJ7D7NJSUEVWEN5MDTMSJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2WGOJ7D7NJSUEVWEN5MDTMSJG/action/storage_attestation","attest_author":"https://pith.science/pith/L2WGOJ7D7NJSUEVWEN5MDTMSJG/action/author_attestation","sign_citation":"https://pith.science/pith/L2WGOJ7D7NJSUEVWEN5MDTMSJG/action/citation_signature","submit_replication":"https://pith.science/pith/L2WGOJ7D7NJSUEVWEN5MDTMSJG/action/replication_record"}},"created_at":"2026-06-25T01:17:46.457282+00:00","updated_at":"2026-06-25T01:17:46.457282+00:00"}