{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KUPLCRVSHAGNRUSOFEAH5SNUS2","short_pith_number":"pith:KUPLCRVS","schema_version":"1.0","canonical_sha256":"551eb146b2380cd8d24e29007ec9b4968b18bed4c1e9329516f128dc34282f30","source":{"kind":"arxiv","id":"2506.12251","version":2},"attestation_state":"computed","paper":{"title":"Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Cristiano Saltori, Marco Pavone, Wenjie Luo, Yan Wang, Yurong You","submitted_at":"2025-06-13T21:56:52Z","abstract_excerpt":"Autoregressive Transformers are increasingly being deployed as end-to-end robot and autonomous vehicle (AV) policy architectures, owing to their scalability and potential to leverage internet-scale pretraining for generalization. Accordingly, tokenizing sensor data efficiently is paramount to ensuring the real-time feasibility of such architectures on embedded hardware. To this end, we present an efficient triplane-based multi-camera tokenization strategy that leverages recent advances in 3D neural reconstruction and rendering to produce sensor tokens that are agnostic to the number of input c"},"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":"2506.12251","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T21:56:52Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"d29cdd21ea7e3d6ed6106e7090730eb9052db60ec1409a58097a59fc13d5997b","abstract_canon_sha256":"234ecf9a1bf5f3448e75fe7bb7b41f07f23b46bfa6a0da77731376b96edd5ea3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:34.609203Z","signature_b64":"SOCPaa9R9iC7T870LDrV4l022EgWBnpllTUlUTrDFlJuWtgH07TNB2FWkmRVtw8jYQm/VW/eupTTlYtwaM6LCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"551eb146b2380cd8d24e29007ec9b4968b18bed4c1e9329516f128dc34282f30","last_reissued_at":"2026-07-05T11:40:34.608687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:34.608687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Cristiano Saltori, Marco Pavone, Wenjie Luo, Yan Wang, Yurong You","submitted_at":"2025-06-13T21:56:52Z","abstract_excerpt":"Autoregressive Transformers are increasingly being deployed as end-to-end robot and autonomous vehicle (AV) policy architectures, owing to their scalability and potential to leverage internet-scale pretraining for generalization. Accordingly, tokenizing sensor data efficiently is paramount to ensuring the real-time feasibility of such architectures on embedded hardware. To this end, we present an efficient triplane-based multi-camera tokenization strategy that leverages recent advances in 3D neural reconstruction and rendering to produce sensor tokens that are agnostic to the number of input c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12251","kind":"arxiv","version":2},"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/2506.12251/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":"2506.12251","created_at":"2026-07-05T11:40:34.608748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12251v2","created_at":"2026-07-05T11:40:34.608748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12251","created_at":"2026-07-05T11:40:34.608748+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUPLCRVSHAGN","created_at":"2026-07-05T11:40:34.608748+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUPLCRVSHAGNRUSO","created_at":"2026-07-05T11:40:34.608748+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUPLCRVS","created_at":"2026-07-05T11:40:34.608748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.17596","citing_title":"PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUPLCRVSHAGNRUSOFEAH5SNUS2","json":"https://pith.science/pith/KUPLCRVSHAGNRUSOFEAH5SNUS2.json","graph_json":"https://pith.science/api/pith-number/KUPLCRVSHAGNRUSOFEAH5SNUS2/graph.json","events_json":"https://pith.science/api/pith-number/KUPLCRVSHAGNRUSOFEAH5SNUS2/events.json","paper":"https://pith.science/paper/KUPLCRVS"},"agent_actions":{"view_html":"https://pith.science/pith/KUPLCRVSHAGNRUSOFEAH5SNUS2","download_json":"https://pith.science/pith/KUPLCRVSHAGNRUSOFEAH5SNUS2.json","view_paper":"https://pith.science/paper/KUPLCRVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12251&json=true","fetch_graph":"https://pith.science/api/pith-number/KUPLCRVSHAGNRUSOFEAH5SNUS2/graph.json","fetch_events":"https://pith.science/api/pith-number/KUPLCRVSHAGNRUSOFEAH5SNUS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUPLCRVSHAGNRUSOFEAH5SNUS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUPLCRVSHAGNRUSOFEAH5SNUS2/action/storage_attestation","attest_author":"https://pith.science/pith/KUPLCRVSHAGNRUSOFEAH5SNUS2/action/author_attestation","sign_citation":"https://pith.science/pith/KUPLCRVSHAGNRUSOFEAH5SNUS2/action/citation_signature","submit_replication":"https://pith.science/pith/KUPLCRVSHAGNRUSOFEAH5SNUS2/action/replication_record"}},"created_at":"2026-07-05T11:40:34.608748+00:00","updated_at":"2026-07-05T11:40:34.608748+00:00"}