{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RG4CVBGCDQOGTOAEKUI56OTRHU","short_pith_number":"pith:RG4CVBGC","schema_version":"1.0","canonical_sha256":"89b82a84c21c1c69b8045511df3a713d16fda428e6bebd7ea5f7d220d2544ae7","source":{"kind":"arxiv","id":"2505.19516","version":1},"attestation_state":"computed","paper":{"title":"DiffE2E: Rethinking End-to-End Driving with a Hybrid Action Diffusion and Supervised Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Fei Gao, Rui Zhao, Yuze Fan, Zhenhai Gao, Ziguo Chen","submitted_at":"2025-05-26T04:58:41Z","abstract_excerpt":"End-to-end learning has emerged as a transformative paradigm in autonomous driving. However, the inherently multimodal nature of driving behaviors and the generalization challenges in long-tail scenarios remain critical obstacles to robust deployment. We propose DiffE2E, a diffusion-based end-to-end autonomous driving framework. This framework first performs multi-scale alignment of multi-sensor perception features through a hierarchical bidirectional cross-attention mechanism. It then introduces a novel class of hybrid diffusion-supervision decoders based on the Transformer architecture, and "},"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":"2505.19516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-26T04:58:41Z","cross_cats_sorted":[],"title_canon_sha256":"53983c37e17565118b669c49a3875220a6ea3700664582c0f1a7ca409e46f115","abstract_canon_sha256":"8294897c51d4dd76e296464bedbb3c1d4d3d859bcb6c83c85cc374794f3f0ede"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:31.671636Z","signature_b64":"1IbZuOnXdhGNWmcmu9LhBo6pqNon+QlXis9fmAQUF5vh8ffRC6iQm/HGBapmdxitRDU7WccgO2mViae4ip+9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89b82a84c21c1c69b8045511df3a713d16fda428e6bebd7ea5f7d220d2544ae7","last_reissued_at":"2026-07-05T11:09:31.671167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:31.671167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffE2E: Rethinking End-to-End Driving with a Hybrid Action Diffusion and Supervised Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Fei Gao, Rui Zhao, Yuze Fan, Zhenhai Gao, Ziguo Chen","submitted_at":"2025-05-26T04:58:41Z","abstract_excerpt":"End-to-end learning has emerged as a transformative paradigm in autonomous driving. However, the inherently multimodal nature of driving behaviors and the generalization challenges in long-tail scenarios remain critical obstacles to robust deployment. We propose DiffE2E, a diffusion-based end-to-end autonomous driving framework. This framework first performs multi-scale alignment of multi-sensor perception features through a hierarchical bidirectional cross-attention mechanism. It then introduces a novel class of hybrid diffusion-supervision decoders based on the Transformer architecture, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19516","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/2505.19516/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":"2505.19516","created_at":"2026-07-05T11:09:31.671212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19516v1","created_at":"2026-07-05T11:09:31.671212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19516","created_at":"2026-07-05T11:09:31.671212+00:00"},{"alias_kind":"pith_short_12","alias_value":"RG4CVBGCDQOG","created_at":"2026-07-05T11:09:31.671212+00:00"},{"alias_kind":"pith_short_16","alias_value":"RG4CVBGCDQOGTOAE","created_at":"2026-07-05T11:09:31.671212+00:00"},{"alias_kind":"pith_short_8","alias_value":"RG4CVBGC","created_at":"2026-07-05T11:09:31.671212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11019","citing_title":"Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2507.17596","citing_title":"PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25329","citing_title":"ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RG4CVBGCDQOGTOAEKUI56OTRHU","json":"https://pith.science/pith/RG4CVBGCDQOGTOAEKUI56OTRHU.json","graph_json":"https://pith.science/api/pith-number/RG4CVBGCDQOGTOAEKUI56OTRHU/graph.json","events_json":"https://pith.science/api/pith-number/RG4CVBGCDQOGTOAEKUI56OTRHU/events.json","paper":"https://pith.science/paper/RG4CVBGC"},"agent_actions":{"view_html":"https://pith.science/pith/RG4CVBGCDQOGTOAEKUI56OTRHU","download_json":"https://pith.science/pith/RG4CVBGCDQOGTOAEKUI56OTRHU.json","view_paper":"https://pith.science/paper/RG4CVBGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19516&json=true","fetch_graph":"https://pith.science/api/pith-number/RG4CVBGCDQOGTOAEKUI56OTRHU/graph.json","fetch_events":"https://pith.science/api/pith-number/RG4CVBGCDQOGTOAEKUI56OTRHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RG4CVBGCDQOGTOAEKUI56OTRHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RG4CVBGCDQOGTOAEKUI56OTRHU/action/storage_attestation","attest_author":"https://pith.science/pith/RG4CVBGCDQOGTOAEKUI56OTRHU/action/author_attestation","sign_citation":"https://pith.science/pith/RG4CVBGCDQOGTOAEKUI56OTRHU/action/citation_signature","submit_replication":"https://pith.science/pith/RG4CVBGCDQOGTOAEKUI56OTRHU/action/replication_record"}},"created_at":"2026-07-05T11:09:31.671212+00:00","updated_at":"2026-07-05T11:09:31.671212+00:00"}