{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6CTORDBGSQC2CQJID6HT4K5JB2","short_pith_number":"pith:6CTORDBG","schema_version":"1.0","canonical_sha256":"f0a6e88c269405a141281f8f3e2ba90e92f56ed7fea29940606789346a829442","source":{"kind":"arxiv","id":"2603.28049","version":3},"attestation_state":"computed","paper":{"title":"Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Drift-AR uses per-position prediction entropy to drive both speculative AR drafting and anti-symmetric drift, achieving genuine single-step visual generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhao, Jie Huang, LinJiang Huang, Mingde Yao, Xiaoxiao Ma, Zhen Zou","submitted_at":"2026-03-30T05:29:00Z","abstract_excerpt":"Autoregressive (AR)-Diffusion hybrid paradigms combine AR's structured semantic modeling with diffusion's high-fidelity synthesis, yet suffer from a dual speed bottleneck: the sequential AR stage and the iterative multi-step denoising of the diffusion vision decode stage. Existing methods address each in isolation without a unified principle design. We observe that the per-position \\emph{prediction entropy} of continuous-space AR models naturally encodes spatially varying generation uncertainty, which simultaneously governing draft prediction quality in the AR stage and reflecting the correcti"},"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":"2603.28049","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-30T05:29:00Z","cross_cats_sorted":[],"title_canon_sha256":"7a7ca910900e6c599693328f78d0f5d89d648faf811b1fbf2e0fce5e3249fb8f","abstract_canon_sha256":"aecd48fee2878fa8a8e06f69fb885fcb35b41d59ca83b56281a6c8795d863191"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:19.488653Z","signature_b64":"fNQ+vkvF1yXfatpw8VYJWzBjiwpWEzvuBKpeVMW5LKGeHIKAjSbagCxtcifUk31ppDGNGiC+W6zo3SEnxBCMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0a6e88c269405a141281f8f3e2ba90e92f56ed7fea29940606789346a829442","last_reissued_at":"2026-06-30T02:17:19.488002Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:19.488002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Drift-AR uses per-position prediction entropy to drive both speculative AR drafting and anti-symmetric drift, achieving genuine single-step visual generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhao, Jie Huang, LinJiang Huang, Mingde Yao, Xiaoxiao Ma, Zhen Zou","submitted_at":"2026-03-30T05:29:00Z","abstract_excerpt":"Autoregressive (AR)-Diffusion hybrid paradigms combine AR's structured semantic modeling with diffusion's high-fidelity synthesis, yet suffer from a dual speed bottleneck: the sequential AR stage and the iterative multi-step denoising of the diffusion vision decode stage. Existing methods address each in isolation without a unified principle design. We observe that the per-position \\emph{prediction entropy} of continuous-space AR models naturally encodes spatially varying generation uncertainty, which simultaneously governing draft prediction quality in the AR stage and reflecting the correcti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Drift-AR leverages entropy signal to accelerate both stages... enabling single-step (1-NFE) decoding without iterative denoising or distillation... Experiments on MAR, TransDiff, and NextStep-1 demonstrate 3.8-5.5× speedup with genuine 1-NFE decoding, matching or surpassing original quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The per-position prediction entropy of continuous-space AR models naturally encodes spatially varying generation uncertainty, which simultaneously governing draft prediction quality in the AR stage and reflecting the corrective effort required by vision decoding stage.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Drift-AR achieves 3.8-5.5x speedup in AR-diffusion image models by using entropy to enable entropy-informed speculative decoding and single-step (1-NFE) anti-symmetric drifting decoding.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Drift-AR uses per-position prediction entropy to drive both speculative AR drafting and anti-symmetric drift, achieving genuine single-step visual generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"dd803163490247bd8f743db9c349ae0fbb8866672a42e0320a03197a4a21a3aa"},"source":{"id":"2603.28049","kind":"arxiv","version":3},"verdict":{"id":"4903fae9-2e79-4fc6-bbe1-0a0da6a6f187","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:59:56.704758Z","strongest_claim":"Drift-AR leverages entropy signal to accelerate both stages... enabling single-step (1-NFE) decoding without iterative denoising or distillation... Experiments on MAR, TransDiff, and NextStep-1 demonstrate 3.8-5.5× speedup with genuine 1-NFE decoding, matching or surpassing original quality.","one_line_summary":"Drift-AR achieves 3.8-5.5x speedup in AR-diffusion image models by using entropy to enable entropy-informed speculative decoding and single-step (1-NFE) anti-symmetric drifting decoding.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The per-position prediction entropy of continuous-space AR models naturally encodes spatially varying generation uncertainty, which simultaneously governing draft prediction quality in the AR stage and reflecting the corrective effort required by vision decoding stage.","pith_extraction_headline":"Drift-AR uses per-position prediction entropy to drive both speculative AR drafting and anti-symmetric drift, achieving genuine single-step visual generation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.28049/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":"2603.28049","created_at":"2026-06-30T02:17:19.488071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.28049v3","created_at":"2026-06-30T02:17:19.488071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28049","created_at":"2026-06-30T02:17:19.488071+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CTORDBGSQC2","created_at":"2026-06-30T02:17:19.488071+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CTORDBGSQC2CQJI","created_at":"2026-06-30T02:17:19.488071+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CTORDBG","created_at":"2026-06-30T02:17:19.488071+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/6CTORDBGSQC2CQJID6HT4K5JB2","json":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2.json","graph_json":"https://pith.science/api/pith-number/6CTORDBGSQC2CQJID6HT4K5JB2/graph.json","events_json":"https://pith.science/api/pith-number/6CTORDBGSQC2CQJID6HT4K5JB2/events.json","paper":"https://pith.science/paper/6CTORDBG"},"agent_actions":{"view_html":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2","download_json":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2.json","view_paper":"https://pith.science/paper/6CTORDBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.28049&json=true","fetch_graph":"https://pith.science/api/pith-number/6CTORDBGSQC2CQJID6HT4K5JB2/graph.json","fetch_events":"https://pith.science/api/pith-number/6CTORDBGSQC2CQJID6HT4K5JB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2/action/storage_attestation","attest_author":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2/action/author_attestation","sign_citation":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2/action/citation_signature","submit_replication":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2/action/replication_record"}},"created_at":"2026-06-30T02:17:19.488071+00:00","updated_at":"2026-06-30T02:17:19.488071+00:00"}