{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:326UJHUXTCOWMVMZ5J4RPBYW76","short_pith_number":"pith:326UJHUX","schema_version":"1.0","canonical_sha256":"debd449e97989d665599ea79178716ff83b0d826824c2e57112d811701cb4792","source":{"kind":"arxiv","id":"2605.11596","version":2},"attestation_state":"computed","paper":{"title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A self-corrective training procedure allows autoregressive driving models to generate minute-scale simulations without drift.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Conglang Zhang, Qian Zhang, Qingjie Wang, Weiqiang Ren, Wei Yin, Xiaoyang Guo, Yifan Zhan, Yinqiang Zheng, Yu Li, Zhanpeng Ouyang, Zhen Dong, Zhengqing Chen, Zihao Yang","submitted_at":"2026-05-12T06:22:16Z","abstract_excerpt":"Closed-loop driving simulation requires real-time interaction beyond short offline clips, pushing current driving world models toward autoregressive (AR) rollout. Existing AR distillation approaches typically rely on frame sinks or student-side degradation training. The former transfers poorly to driving due to fast ego-motion and rapid scene changes, while the latter remains bounded by the teacher's single-pass output length and thus provides only a limited supervision horizon. A natural question is: can the teacher itself be extended via AR rollout to provide unbounded-horizon supervision at"},"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":"2605.11596","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T06:22:16Z","cross_cats_sorted":[],"title_canon_sha256":"c4ad949a14b568f8083f9ad34e5d650ead12d3c2594543e4b8f93f1640895ef5","abstract_canon_sha256":"ead24f09913ab77de5cd3b54efde69c3eb4e2c382a1e340ade73762b9f3e0957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:23.462516Z","signature_b64":"k3Tas/6p4e9B5BOtIwngurG1vGvsyOYpV7MW1Xk4v7E5VFU9PyXak6Q26qpPecuFbKt9baechFr2hbFQJhH+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"debd449e97989d665599ea79178716ff83b0d826824c2e57112d811701cb4792","last_reissued_at":"2026-05-25T02:01:23.461727Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:23.461727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A self-corrective training procedure allows autoregressive driving models to generate minute-scale simulations without drift.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Conglang Zhang, Qian Zhang, Qingjie Wang, Weiqiang Ren, Wei Yin, Xiaoyang Guo, Yifan Zhan, Yinqiang Zheng, Yu Li, Zhanpeng Ouyang, Zhen Dong, Zhengqing Chen, Zihao Yang","submitted_at":"2026-05-12T06:22:16Z","abstract_excerpt":"Closed-loop driving simulation requires real-time interaction beyond short offline clips, pushing current driving world models toward autoregressive (AR) rollout. Existing AR distillation approaches typically rely on frame sinks or student-side degradation training. The former transfers poorly to driving due to fast ego-motion and rapid scene changes, while the latter remains bounded by the teacher's single-pass output length and thus provides only a limited supervision horizon. A natural question is: can the teacher itself be extended via AR rollout to provide unbounded-horizon supervision at"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"HorizonDrive natively supports minute-scale AR rollout under bounded memory; on nuScenes, HorizonDrive reduces FID by 52% and FVD by 37%, and lowers ARE and DTW by 21% and 9% relative to the strongest long-horizon streaming baselines, while remaining competitive with single-pass driving video generators.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That training with scheduled rollout recovery produces a teacher model that remains stable and provides reliable supervision across long autoregressive rollouts without introducing new biases or artifacts not present in ground truth.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HorizonDrive enables stable long-horizon autoregressive driving simulation via anti-drifting teacher training with scheduled rollout recovery and teacher rollout distillation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A self-corrective training procedure allows autoregressive driving models to generate minute-scale simulations without drift.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2a80e299f8a0859887f0b1630f4237f65d4f263b12f3635ca9bec815622c0d5e"},"source":{"id":"2605.11596","kind":"arxiv","version":2},"verdict":{"id":"316ef20e-919e-40be-9c5d-b6dc7fe84031","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T01:12:39.233806Z","strongest_claim":"HorizonDrive natively supports minute-scale AR rollout under bounded memory; on nuScenes, HorizonDrive reduces FID by 52% and FVD by 37%, and lowers ARE and DTW by 21% and 9% relative to the strongest long-horizon streaming baselines, while remaining competitive with single-pass driving video generators.","one_line_summary":"HorizonDrive enables stable long-horizon autoregressive driving simulation via anti-drifting teacher training with scheduled rollout recovery and teacher rollout distillation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That training with scheduled rollout recovery produces a teacher model that remains stable and provides reliable supervision across long autoregressive rollouts without introducing new biases or artifacts not present in ground truth.","pith_extraction_headline":"A self-corrective training procedure allows autoregressive driving models to generate minute-scale simulations without drift."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11596/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-21T01:01:33.499523Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T15:54:54.973651Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-20T04:02:00.490529Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T12:33:25.843749Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0dd64dfb3edc119fce7af09a02d03e128fcfd73489dc7c257b49e366115a8d83"},"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":"2605.11596","created_at":"2026-05-25T02:01:23.461869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11596v2","created_at":"2026-05-25T02:01:23.461869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11596","created_at":"2026-05-25T02:01:23.461869+00:00"},{"alias_kind":"pith_short_12","alias_value":"326UJHUXTCOW","created_at":"2026-05-25T02:01:23.461869+00:00"},{"alias_kind":"pith_short_16","alias_value":"326UJHUXTCOWMVMZ","created_at":"2026-05-25T02:01:23.461869+00:00"},{"alias_kind":"pith_short_8","alias_value":"326UJHUX","created_at":"2026-05-25T02:01:23.461869+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/326UJHUXTCOWMVMZ5J4RPBYW76","json":"https://pith.science/pith/326UJHUXTCOWMVMZ5J4RPBYW76.json","graph_json":"https://pith.science/api/pith-number/326UJHUXTCOWMVMZ5J4RPBYW76/graph.json","events_json":"https://pith.science/api/pith-number/326UJHUXTCOWMVMZ5J4RPBYW76/events.json","paper":"https://pith.science/paper/326UJHUX"},"agent_actions":{"view_html":"https://pith.science/pith/326UJHUXTCOWMVMZ5J4RPBYW76","download_json":"https://pith.science/pith/326UJHUXTCOWMVMZ5J4RPBYW76.json","view_paper":"https://pith.science/paper/326UJHUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11596&json=true","fetch_graph":"https://pith.science/api/pith-number/326UJHUXTCOWMVMZ5J4RPBYW76/graph.json","fetch_events":"https://pith.science/api/pith-number/326UJHUXTCOWMVMZ5J4RPBYW76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/326UJHUXTCOWMVMZ5J4RPBYW76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/326UJHUXTCOWMVMZ5J4RPBYW76/action/storage_attestation","attest_author":"https://pith.science/pith/326UJHUXTCOWMVMZ5J4RPBYW76/action/author_attestation","sign_citation":"https://pith.science/pith/326UJHUXTCOWMVMZ5J4RPBYW76/action/citation_signature","submit_replication":"https://pith.science/pith/326UJHUXTCOWMVMZ5J4RPBYW76/action/replication_record"}},"created_at":"2026-05-25T02:01:23.461869+00:00","updated_at":"2026-05-25T02:01:23.461869+00:00"}