{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XO2YJ7CMMMUDTQYWWQWHC2266O","short_pith_number":"pith:XO2YJ7CM","schema_version":"1.0","canonical_sha256":"bbb584fc4c632839c316b42c716b5ef3a894b24a27f4c6445ecc28ebfaa9b53e","source":{"kind":"arxiv","id":"2506.24113","version":1},"attestation_state":"computed","paper":{"title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingwei Huang, Kaiwen Zhang, Li Yuan, Qian Zhang, Wei Yin, Xiaotao Hu, Xiao-Xiao Long, Xiaoyang Guo, Xingang Pan, Xun Cao, Yuan Liu, Zhenyu Tang","submitted_at":"2025-06-30T17:56:35Z","abstract_excerpt":"Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-based world models struggle with flexible-length, long-horizon predictions and integrating trajectory planning. This is because conventional video diffusion models rely on global joint distribution modeling of fixed-length frame sequences rather than sequentially constructing localized distributions at each timestep. In this work, we propose Epona, an autoregressive diffusion world model that enables localized spatiote"},"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":"2506.24113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T17:56:35Z","cross_cats_sorted":[],"title_canon_sha256":"1bb66908695f1c58743cebd0069ed1c58a4d92159af967ab2895271e4e89d225","abstract_canon_sha256":"e3a53db3184aea648127f6b3a516da507f8fd39ec99fb50d5891015584e5fae5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:33.334619Z","signature_b64":"bXfOz6oYPfdJdS1fgbzswKg0bUD6/x7jXL1Kv7DmVtu9pOhw2PbQh7ddmg02AMw+DDW+l0nqbqwTRTddxsnDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbb584fc4c632839c316b42c716b5ef3a894b24a27f4c6445ecc28ebfaa9b53e","last_reissued_at":"2026-07-05T11:29:33.333828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:33.333828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingwei Huang, Kaiwen Zhang, Li Yuan, Qian Zhang, Wei Yin, Xiaotao Hu, Xiao-Xiao Long, Xiaoyang Guo, Xingang Pan, Xun Cao, Yuan Liu, Zhenyu Tang","submitted_at":"2025-06-30T17:56:35Z","abstract_excerpt":"Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-based world models struggle with flexible-length, long-horizon predictions and integrating trajectory planning. This is because conventional video diffusion models rely on global joint distribution modeling of fixed-length frame sequences rather than sequentially constructing localized distributions at each timestep. In this work, we propose Epona, an autoregressive diffusion world model that enables localized spatiote"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.24113","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/2506.24113/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":"2506.24113","created_at":"2026-07-05T11:29:33.333933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.24113v1","created_at":"2026-07-05T11:29:33.333933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.24113","created_at":"2026-07-05T11:29:33.333933+00:00"},{"alias_kind":"pith_short_12","alias_value":"XO2YJ7CMMMUD","created_at":"2026-07-05T11:29:33.333933+00:00"},{"alias_kind":"pith_short_16","alias_value":"XO2YJ7CMMMUDTQYW","created_at":"2026-07-05T11:29:33.333933+00:00"},{"alias_kind":"pith_short_8","alias_value":"XO2YJ7CM","created_at":"2026-07-05T11:29:33.333933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22913","citing_title":"Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20110","citing_title":"FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27504","citing_title":"ReWorld: Learning Better Representations for World Action Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11596","citing_title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22089","citing_title":"LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19242","citing_title":"PhyWorld: Physics-Faithful World Model for Video Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23421","citing_title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19675","citing_title":"DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11596","citing_title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16592","citing_title":"Human Cognition in Machines: A Unified Perspective of World Models","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02762","citing_title":"Unified Map Prior Encoder for Mapping and Planning","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XO2YJ7CMMMUDTQYWWQWHC2266O","json":"https://pith.science/pith/XO2YJ7CMMMUDTQYWWQWHC2266O.json","graph_json":"https://pith.science/api/pith-number/XO2YJ7CMMMUDTQYWWQWHC2266O/graph.json","events_json":"https://pith.science/api/pith-number/XO2YJ7CMMMUDTQYWWQWHC2266O/events.json","paper":"https://pith.science/paper/XO2YJ7CM"},"agent_actions":{"view_html":"https://pith.science/pith/XO2YJ7CMMMUDTQYWWQWHC2266O","download_json":"https://pith.science/pith/XO2YJ7CMMMUDTQYWWQWHC2266O.json","view_paper":"https://pith.science/paper/XO2YJ7CM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.24113&json=true","fetch_graph":"https://pith.science/api/pith-number/XO2YJ7CMMMUDTQYWWQWHC2266O/graph.json","fetch_events":"https://pith.science/api/pith-number/XO2YJ7CMMMUDTQYWWQWHC2266O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XO2YJ7CMMMUDTQYWWQWHC2266O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XO2YJ7CMMMUDTQYWWQWHC2266O/action/storage_attestation","attest_author":"https://pith.science/pith/XO2YJ7CMMMUDTQYWWQWHC2266O/action/author_attestation","sign_citation":"https://pith.science/pith/XO2YJ7CMMMUDTQYWWQWHC2266O/action/citation_signature","submit_replication":"https://pith.science/pith/XO2YJ7CMMMUDTQYWWQWHC2266O/action/replication_record"}},"created_at":"2026-07-05T11:29:33.333933+00:00","updated_at":"2026-07-05T11:29:33.333933+00:00"}