{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6CTORDBGSQC2CQJID6HT4K5JB2","short_pith_number":"pith:6CTORDBG","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"},"canonical_sha256":"f0a6e88c269405a141281f8f3e2ba90e92f56ed7fea29940606789346a829442","source":{"kind":"arxiv","id":"2603.28049","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.28049","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2603.28049v3","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28049","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"6CTORDBGSQC2","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"6CTORDBGSQC2CQJI","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"6CTORDBG","created_at":"2026-06-30T02:17:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6CTORDBGSQC2CQJID6HT4K5JB2","target":"record","payload":{"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"},"canonical_sha256":"f0a6e88c269405a141281f8f3e2ba90e92f56ed7fea29940606789346a829442","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"},"source_kind":"arxiv","source_id":"2603.28049","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"loggWQrxHGOdffgPuDPeL9r9JyA2Kw+dL0ZN7Kv5077v4pEawpMKBtsCsGhQd12v5YRWfFdBuJ9zzgSkAP49Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:24:35.884100Z"},"content_sha256":"bb35625b2d64bb5d6dce4c5d6684fcc9dcc2e5080730fb733c660f9e6916b50f","schema_version":"1.0","event_id":"sha256:bb35625b2d64bb5d6dce4c5d6684fcc9dcc2e5080730fb733c660f9e6916b50f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6CTORDBGSQC2CQJID6HT4K5JB2","target":"graph","payload":{"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"},"verdict_id":"4903fae9-2e79-4fc6-bbe1-0a0da6a6f187"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h2fWV4b4FfluDPL2K3cy4J1JczdecjpLXR3EpChnoiP/x2ZoENFVCU/ExA0AdpX65GsTMAj5yxhNFCHl28O6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:24:35.884672Z"},"content_sha256":"587c593bc3fcda71a61e670b3d492fe0f3ab960c41c0e023fd4776223587e518","schema_version":"1.0","event_id":"sha256:587c593bc3fcda71a61e670b3d492fe0f3ab960c41c0e023fd4776223587e518"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2/bundle.json","state_url":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CTORDBGSQC2CQJID6HT4K5JB2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T07:24:35Z","links":{"resolver":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2","bundle":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2/bundle.json","state":"https://pith.science/pith/6CTORDBGSQC2CQJID6HT4K5JB2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CTORDBGSQC2CQJID6HT4K5JB2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6CTORDBGSQC2CQJID6HT4K5JB2","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":"aecd48fee2878fa8a8e06f69fb885fcb35b41d59ca83b56281a6c8795d863191","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-30T05:29:00Z","title_canon_sha256":"7a7ca910900e6c599693328f78d0f5d89d648faf811b1fbf2e0fce5e3249fb8f"},"schema_version":"1.0","source":{"id":"2603.28049","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.28049","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2603.28049v3","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28049","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"6CTORDBGSQC2","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"6CTORDBGSQC2CQJI","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"6CTORDBG","created_at":"2026-06-30T02:17:19Z"}],"graph_snapshots":[{"event_id":"sha256:587c593bc3fcda71a61e670b3d492fe0f3ab960c41c0e023fd4776223587e518","target":"graph","created_at":"2026-06-30T02:17:19Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Drift-AR uses per-position prediction entropy to drive both speculative AR drafting and anti-symmetric drift, achieving genuine single-step visual generation."}],"snapshot_sha256":"dd803163490247bd8f743db9c349ae0fbb8866672a42e0320a03197a4a21a3aa"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.28049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Feng Zhao, Jie Huang, LinJiang Huang, Mingde Yao, Xiaoxiao Ma, Zhen Zou","cross_cats":[],"headline":"Drift-AR uses per-position prediction entropy to drive both speculative AR drafting and anti-symmetric drift, achieving genuine single-step visual generation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-30T05:29:00Z","title":"Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.28049","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-14T21:59:56.704758Z","id":"4903fae9-2e79-4fc6-bbe1-0a0da6a6f187","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"4903fae9-2e79-4fc6-bbe1-0a0da6a6f187"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bb35625b2d64bb5d6dce4c5d6684fcc9dcc2e5080730fb733c660f9e6916b50f","target":"record","created_at":"2026-06-30T02:17:19Z","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":"aecd48fee2878fa8a8e06f69fb885fcb35b41d59ca83b56281a6c8795d863191","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-30T05:29:00Z","title_canon_sha256":"7a7ca910900e6c599693328f78d0f5d89d648faf811b1fbf2e0fce5e3249fb8f"},"schema_version":"1.0","source":{"id":"2603.28049","kind":"arxiv","version":3}},"canonical_sha256":"f0a6e88c269405a141281f8f3e2ba90e92f56ed7fea29940606789346a829442","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0a6e88c269405a141281f8f3e2ba90e92f56ed7fea29940606789346a829442","first_computed_at":"2026-06-30T02:17:19.488002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:19.488002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fNQ+vkvF1yXfatpw8VYJWzBjiwpWEzvuBKpeVMW5LKGeHIKAjSbagCxtcifUk31ppDGNGiC+W6zo3SEnxBCMDg==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:19.488653Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.28049","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb35625b2d64bb5d6dce4c5d6684fcc9dcc2e5080730fb733c660f9e6916b50f","sha256:587c593bc3fcda71a61e670b3d492fe0f3ab960c41c0e023fd4776223587e518"],"state_sha256":"b49fb458e439f4a4359e6e79eeb1ebbce3b04696b8e9851478dd8d3a287be92d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"REp+ZL8ABJcnNyvUPpxKfc+mzKukX3LARzJgxvaRddkVNosGJnU4FnwRrZb8KoJ+HmshSX3YTrBJw+f1cP1wBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:24:35.888274Z","bundle_sha256":"206099c2ca1c0f48c9df10b96990571027434bed738c12cbda33a54010c5b2a0"}}