{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:72OE4WA4YI2ECQW6T4H22EAUSV","short_pith_number":"pith:72OE4WA4","schema_version":"1.0","canonical_sha256":"fe9c4e581cc2344142de9f0fad1014954e65f23d3ad5dd633d92a46b177fa7fb","source":{"kind":"arxiv","id":"2506.13138","version":3},"attestation_state":"computed","paper":{"title":"STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Wu, Jiamin Wang, Qingqiu Huang, Xiang Feng, Xinge Zhu, Yaming Wang, Yichen Yao, Yuexin Ma","submitted_at":"2025-06-16T06:53:05Z","abstract_excerpt":"The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation and feature misalignment due to inadequate decoupling of spatio-temporal dynamics and limited cross-frame feature propagation mechanisms. To address these limitations, we present STAGE (Streaming Temporal Attention Generative Engine), a novel auto-regressive framework that pioneers hierarchical feature coordination and multi-phase optimization for sustainable video synthesis. "},"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":"2506.13138","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-16T06:53:05Z","cross_cats_sorted":[],"title_canon_sha256":"8256a8b1d10125db7b1173b1bca21872e66dc3b0bcf8025feb9967c76b486863","abstract_canon_sha256":"3df6aef7f0425c965f6d32fbf9e0bf40f766a841ae40c4598566d3733a75fd0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:02.759871Z","signature_b64":"MrgtmkwW9lVuMlkR2dC4U0KI0RKVXYD+u2rgBkLPLh4hpftKI269RdhfA8gqOYNMRtC8105Hf/NdBnGlZGtbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe9c4e581cc2344142de9f0fad1014954e65f23d3ad5dd633d92a46b177fa7fb","last_reissued_at":"2026-07-05T12:02:02.759367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:02.759367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Wu, Jiamin Wang, Qingqiu Huang, Xiang Feng, Xinge Zhu, Yaming Wang, Yichen Yao, Yuexin Ma","submitted_at":"2025-06-16T06:53:05Z","abstract_excerpt":"The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation and feature misalignment due to inadequate decoupling of spatio-temporal dynamics and limited cross-frame feature propagation mechanisms. To address these limitations, we present STAGE (Streaming Temporal Attention Generative Engine), a novel auto-regressive framework that pioneers hierarchical feature coordination and multi-phase optimization for sustainable video synthesis. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13138","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/2506.13138/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":"2506.13138","created_at":"2026-07-05T12:02:02.759426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13138v3","created_at":"2026-07-05T12:02:02.759426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13138","created_at":"2026-07-05T12:02:02.759426+00:00"},{"alias_kind":"pith_short_12","alias_value":"72OE4WA4YI2E","created_at":"2026-07-05T12:02:02.759426+00:00"},{"alias_kind":"pith_short_16","alias_value":"72OE4WA4YI2ECQW6","created_at":"2026-07-05T12:02:02.759426+00:00"},{"alias_kind":"pith_short_8","alias_value":"72OE4WA4","created_at":"2026-07-05T12:02:02.759426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"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":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72OE4WA4YI2ECQW6T4H22EAUSV","json":"https://pith.science/pith/72OE4WA4YI2ECQW6T4H22EAUSV.json","graph_json":"https://pith.science/api/pith-number/72OE4WA4YI2ECQW6T4H22EAUSV/graph.json","events_json":"https://pith.science/api/pith-number/72OE4WA4YI2ECQW6T4H22EAUSV/events.json","paper":"https://pith.science/paper/72OE4WA4"},"agent_actions":{"view_html":"https://pith.science/pith/72OE4WA4YI2ECQW6T4H22EAUSV","download_json":"https://pith.science/pith/72OE4WA4YI2ECQW6T4H22EAUSV.json","view_paper":"https://pith.science/paper/72OE4WA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13138&json=true","fetch_graph":"https://pith.science/api/pith-number/72OE4WA4YI2ECQW6T4H22EAUSV/graph.json","fetch_events":"https://pith.science/api/pith-number/72OE4WA4YI2ECQW6T4H22EAUSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72OE4WA4YI2ECQW6T4H22EAUSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72OE4WA4YI2ECQW6T4H22EAUSV/action/storage_attestation","attest_author":"https://pith.science/pith/72OE4WA4YI2ECQW6T4H22EAUSV/action/author_attestation","sign_citation":"https://pith.science/pith/72OE4WA4YI2ECQW6T4H22EAUSV/action/citation_signature","submit_replication":"https://pith.science/pith/72OE4WA4YI2ECQW6T4H22EAUSV/action/replication_record"}},"created_at":"2026-07-05T12:02:02.759426+00:00","updated_at":"2026-07-05T12:02:02.759426+00:00"}