{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SSA6X2ZPABMO5FP7PFLQ7IFEVD","short_pith_number":"pith:SSA6X2ZP","schema_version":"1.0","canonical_sha256":"9481ebeb2f0058ee95ff79570fa0a4a8d8eabf8fa842bb4c8688de62a91b2925","source":{"kind":"arxiv","id":"2104.09224","version":1},"attestation_state":"computed","paper":{"title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aditya Prakash, Andreas Geiger, Kashyap Chitta","submitted_at":"2021-04-19T11:48:13Z","abstract_excerpt":"How should representations from complementary sensors be integrated for autonomous driving? Geometry-based sensor fusion has shown great promise for perception tasks such as object detection and motion forecasting. However, for the actual driving task, the global context of the 3D scene is key, e.g. a change in traffic light state can affect the behavior of a vehicle geometrically distant from that traffic light. Geometry alone may therefore be insufficient for effectively fusing representations in end-to-end driving models. In this work, we demonstrate that imitation learning policies based o"},"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":"2104.09224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-19T11:48:13Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"438d9d34955cc8e3ad5b489378125631237e498f7514d0c1f31c836e91b58b15","abstract_canon_sha256":"1d097fd1a91601c9d204ff0235eed968602d601bd86798118b47f57be3757bb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:10.796256Z","signature_b64":"mheTa28xGVQLDv8nzdJdvzNayQKoeCvRU2Snn8fweOcEwmdICB4WT2yt9H6s4N/+kyaNOiX6oLsJW6UpmNMgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9481ebeb2f0058ee95ff79570fa0a4a8d8eabf8fa842bb4c8688de62a91b2925","last_reissued_at":"2026-07-05T02:33:10.795861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:10.795861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aditya Prakash, Andreas Geiger, Kashyap Chitta","submitted_at":"2021-04-19T11:48:13Z","abstract_excerpt":"How should representations from complementary sensors be integrated for autonomous driving? Geometry-based sensor fusion has shown great promise for perception tasks such as object detection and motion forecasting. However, for the actual driving task, the global context of the 3D scene is key, e.g. a change in traffic light state can affect the behavior of a vehicle geometrically distant from that traffic light. Geometry alone may therefore be insufficient for effectively fusing representations in end-to-end driving models. In this work, we demonstrate that imitation learning policies based o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09224","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/2104.09224/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":"2104.09224","created_at":"2026-07-05T02:33:10.795920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.09224v1","created_at":"2026-07-05T02:33:10.795920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09224","created_at":"2026-07-05T02:33:10.795920+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSA6X2ZPABMO","created_at":"2026-07-05T02:33:10.795920+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSA6X2ZPABMO5FP7","created_at":"2026-07-05T02:33:10.795920+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSA6X2ZP","created_at":"2026-07-05T02:33:10.795920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04355","citing_title":"InterFuserDVS: Event-Enhanced Sensor Fusion for Safe RL-Based Decision Making","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSA6X2ZPABMO5FP7PFLQ7IFEVD","json":"https://pith.science/pith/SSA6X2ZPABMO5FP7PFLQ7IFEVD.json","graph_json":"https://pith.science/api/pith-number/SSA6X2ZPABMO5FP7PFLQ7IFEVD/graph.json","events_json":"https://pith.science/api/pith-number/SSA6X2ZPABMO5FP7PFLQ7IFEVD/events.json","paper":"https://pith.science/paper/SSA6X2ZP"},"agent_actions":{"view_html":"https://pith.science/pith/SSA6X2ZPABMO5FP7PFLQ7IFEVD","download_json":"https://pith.science/pith/SSA6X2ZPABMO5FP7PFLQ7IFEVD.json","view_paper":"https://pith.science/paper/SSA6X2ZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.09224&json=true","fetch_graph":"https://pith.science/api/pith-number/SSA6X2ZPABMO5FP7PFLQ7IFEVD/graph.json","fetch_events":"https://pith.science/api/pith-number/SSA6X2ZPABMO5FP7PFLQ7IFEVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSA6X2ZPABMO5FP7PFLQ7IFEVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSA6X2ZPABMO5FP7PFLQ7IFEVD/action/storage_attestation","attest_author":"https://pith.science/pith/SSA6X2ZPABMO5FP7PFLQ7IFEVD/action/author_attestation","sign_citation":"https://pith.science/pith/SSA6X2ZPABMO5FP7PFLQ7IFEVD/action/citation_signature","submit_replication":"https://pith.science/pith/SSA6X2ZPABMO5FP7PFLQ7IFEVD/action/replication_record"}},"created_at":"2026-07-05T02:33:10.795920+00:00","updated_at":"2026-07-05T02:33:10.795920+00:00"}