{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WCX2BY2FWVOJ2VWSGSVZIC77SP","short_pith_number":"pith:WCX2BY2F","schema_version":"1.0","canonical_sha256":"b0afa0e345b55c9d56d234ab940bff93f26315baaad88cd23257c3c18f89815e","source":{"kind":"arxiv","id":"2312.14606","version":1},"attestation_state":"computed","paper":{"title":"Explainable Multi-Camera 3D Object Detection with Transformer-Based Saliency Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lutz Eckstein, Till Beemelmanns, Wassim Zahr","submitted_at":"2023-12-22T11:03:12Z","abstract_excerpt":"Vision Transformers (ViTs) have achieved state-of-the-art results on various computer vision tasks, including 3D object detection. However, their end-to-end implementation also makes ViTs less explainable, which can be a challenge for deploying them in safety-critical applications, such as autonomous driving, where it is important for authorities, developers, and users to understand the model's reasoning behind its predictions. In this paper, we propose a novel method for generating saliency maps for a DetR-like ViT with multiple camera inputs used for 3D object detection. Our method is based "},"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":"2312.14606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T11:03:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d1a539ae7de6d9224402514de85dff340456c23a47151eda6dc003da0d80770","abstract_canon_sha256":"409353d33f192ab8d258b3d38d393994116eb6e6079be31e5c9e824018d001f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:17.675573Z","signature_b64":"lIvNH+fFLu1BlkMzsgOntfNTDFYbnm54M9ysemFEEyDnDrqLYAZ1YFEenu3m2ZLoQe8z/XNyt3IEv0WW/h1WCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0afa0e345b55c9d56d234ab940bff93f26315baaad88cd23257c3c18f89815e","last_reissued_at":"2026-07-05T07:27:17.675106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:17.675106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable Multi-Camera 3D Object Detection with Transformer-Based Saliency Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lutz Eckstein, Till Beemelmanns, Wassim Zahr","submitted_at":"2023-12-22T11:03:12Z","abstract_excerpt":"Vision Transformers (ViTs) have achieved state-of-the-art results on various computer vision tasks, including 3D object detection. However, their end-to-end implementation also makes ViTs less explainable, which can be a challenge for deploying them in safety-critical applications, such as autonomous driving, where it is important for authorities, developers, and users to understand the model's reasoning behind its predictions. In this paper, we propose a novel method for generating saliency maps for a DetR-like ViT with multiple camera inputs used for 3D object detection. Our method is based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14606","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/2312.14606/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":"2312.14606","created_at":"2026-07-05T07:27:17.675163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14606v1","created_at":"2026-07-05T07:27:17.675163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14606","created_at":"2026-07-05T07:27:17.675163+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCX2BY2FWVOJ","created_at":"2026-07-05T07:27:17.675163+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCX2BY2FWVOJ2VWS","created_at":"2026-07-05T07:27:17.675163+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCX2BY2F","created_at":"2026-07-05T07:27:17.675163+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/WCX2BY2FWVOJ2VWSGSVZIC77SP","json":"https://pith.science/pith/WCX2BY2FWVOJ2VWSGSVZIC77SP.json","graph_json":"https://pith.science/api/pith-number/WCX2BY2FWVOJ2VWSGSVZIC77SP/graph.json","events_json":"https://pith.science/api/pith-number/WCX2BY2FWVOJ2VWSGSVZIC77SP/events.json","paper":"https://pith.science/paper/WCX2BY2F"},"agent_actions":{"view_html":"https://pith.science/pith/WCX2BY2FWVOJ2VWSGSVZIC77SP","download_json":"https://pith.science/pith/WCX2BY2FWVOJ2VWSGSVZIC77SP.json","view_paper":"https://pith.science/paper/WCX2BY2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14606&json=true","fetch_graph":"https://pith.science/api/pith-number/WCX2BY2FWVOJ2VWSGSVZIC77SP/graph.json","fetch_events":"https://pith.science/api/pith-number/WCX2BY2FWVOJ2VWSGSVZIC77SP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCX2BY2FWVOJ2VWSGSVZIC77SP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCX2BY2FWVOJ2VWSGSVZIC77SP/action/storage_attestation","attest_author":"https://pith.science/pith/WCX2BY2FWVOJ2VWSGSVZIC77SP/action/author_attestation","sign_citation":"https://pith.science/pith/WCX2BY2FWVOJ2VWSGSVZIC77SP/action/citation_signature","submit_replication":"https://pith.science/pith/WCX2BY2FWVOJ2VWSGSVZIC77SP/action/replication_record"}},"created_at":"2026-07-05T07:27:17.675163+00:00","updated_at":"2026-07-05T07:27:17.675163+00:00"}