{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZMHOH3BK5UIKX6RNWY7AE7MX7O","short_pith_number":"pith:ZMHOH3BK","schema_version":"1.0","canonical_sha256":"cb0ee3ec2aed10abfa2db63e027d97fb9efa149552c1fcceb3f570089c7fd3bf","source":{"kind":"arxiv","id":"2606.02105","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Action Diffusion for Robust End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio M. L\\'opez Pe\\~na, Diego Porres, Gabriel Villalonga Pineda, Jorge Daniel Rodr\\'iguez-Vidal","submitted_at":"2026-06-01T11:35:35Z","abstract_excerpt":"End-to-End Autonomous Driving (E2E-AD) systems have largely converged on predicting intermediate trajectory waypoints, delegating final control to hand-crafted controllers with GPS access. Direct control-signal prediction (outputting throttle, steer and brake in an end-to-end fashion) remains underexplored, and critically, the role of action multimodality in such systems is not well understood. We argue that moving beyond deterministic, single-action outputs is not merely a modelling choice, but a key driver of driving performance, representational quality, and training stability. To validate "},"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":"2606.02105","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T11:35:35Z","cross_cats_sorted":[],"title_canon_sha256":"85df1bb487581d3c103bc0b305300ab15cd11663302d7226133515d19a181406","abstract_canon_sha256":"021adb12fe50b3d77c57615f9c79870447a53748b8779b0eaa17b9b66a779594"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:06.632576Z","signature_b64":"hKpHvczGThTBlxbweywaU5kj1E97KwfgFeQrM6hLUlFqk1nUCV918lTPEUfVrbE+HB3Vv4+WEmHfZlMx4gFJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb0ee3ec2aed10abfa2db63e027d97fb9efa149552c1fcceb3f570089c7fd3bf","last_reissued_at":"2026-06-02T02:05:06.632195Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:06.632195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Action Diffusion for Robust End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio M. L\\'opez Pe\\~na, Diego Porres, Gabriel Villalonga Pineda, Jorge Daniel Rodr\\'iguez-Vidal","submitted_at":"2026-06-01T11:35:35Z","abstract_excerpt":"End-to-End Autonomous Driving (E2E-AD) systems have largely converged on predicting intermediate trajectory waypoints, delegating final control to hand-crafted controllers with GPS access. Direct control-signal prediction (outputting throttle, steer and brake in an end-to-end fashion) remains underexplored, and critically, the role of action multimodality in such systems is not well understood. We argue that moving beyond deterministic, single-action outputs is not merely a modelling choice, but a key driver of driving performance, representational quality, and training stability. To validate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02105","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/2606.02105/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":"2606.02105","created_at":"2026-06-02T02:05:06.632250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02105v1","created_at":"2026-06-02T02:05:06.632250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02105","created_at":"2026-06-02T02:05:06.632250+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMHOH3BK5UIK","created_at":"2026-06-02T02:05:06.632250+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMHOH3BK5UIKX6RN","created_at":"2026-06-02T02:05:06.632250+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMHOH3BK","created_at":"2026-06-02T02:05:06.632250+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/ZMHOH3BK5UIKX6RNWY7AE7MX7O","json":"https://pith.science/pith/ZMHOH3BK5UIKX6RNWY7AE7MX7O.json","graph_json":"https://pith.science/api/pith-number/ZMHOH3BK5UIKX6RNWY7AE7MX7O/graph.json","events_json":"https://pith.science/api/pith-number/ZMHOH3BK5UIKX6RNWY7AE7MX7O/events.json","paper":"https://pith.science/paper/ZMHOH3BK"},"agent_actions":{"view_html":"https://pith.science/pith/ZMHOH3BK5UIKX6RNWY7AE7MX7O","download_json":"https://pith.science/pith/ZMHOH3BK5UIKX6RNWY7AE7MX7O.json","view_paper":"https://pith.science/paper/ZMHOH3BK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02105&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMHOH3BK5UIKX6RNWY7AE7MX7O/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMHOH3BK5UIKX6RNWY7AE7MX7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMHOH3BK5UIKX6RNWY7AE7MX7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMHOH3BK5UIKX6RNWY7AE7MX7O/action/storage_attestation","attest_author":"https://pith.science/pith/ZMHOH3BK5UIKX6RNWY7AE7MX7O/action/author_attestation","sign_citation":"https://pith.science/pith/ZMHOH3BK5UIKX6RNWY7AE7MX7O/action/citation_signature","submit_replication":"https://pith.science/pith/ZMHOH3BK5UIKX6RNWY7AE7MX7O/action/replication_record"}},"created_at":"2026-06-02T02:05:06.632250+00:00","updated_at":"2026-06-02T02:05:06.632250+00:00"}