{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PQ2PMH6XQA265G2RRM7ZQE37ZO","short_pith_number":"pith:PQ2PMH6X","schema_version":"1.0","canonical_sha256":"7c34f61fd78035ee9b518b3f98137fcb8ecc1c4baf1b0f335ee564d55047d7ff","source":{"kind":"arxiv","id":"2607.23511","version":1},"attestation_state":"computed","paper":{"title":"MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Donglin Di, Hao Li, Lei Fan, Xuancheng Zhang, Xun Yang, Zhijing Cheng","submitted_at":"2026-07-26T07:20:57Z","abstract_excerpt":"End-to-end autonomous driving systems commonly follow a cascaded two-stage pipeline where a perception stage compresses multi-modal sensor inputs into a compact context and a downstream planner predicts trajectories conditioned on this context. We argue that this one-way perception-to-planning interface forces sensor inputs into a compact representation, losing the fine-grained details critical for planning. Moreover, by constraining the planner to this compressed context, it is difficult to leverage the rich representations offered by modern vision foundation models. To address these issues, "},"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":"2607.23511","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-26T07:20:57Z","cross_cats_sorted":[],"title_canon_sha256":"fc9d99ca86ca1d260dc59d7fc861d93fdc9c7e10e3137865c6e399e938769d5c","abstract_canon_sha256":"5b9107719c76c13ecc289029f74b8f4df21f03195f87f3a62e8002c3cdb42592"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:56.770632Z","signature_b64":"sd3dRgjawB5tBFcrOCHhS+fMCG5dDiJ97fR7FNlsFkWBnafx6yOXHpUqRGWgHq+bi4+JTyES9kvElhmEmy5jCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c34f61fd78035ee9b518b3f98137fcb8ecc1c4baf1b0f335ee564d55047d7ff","last_reissued_at":"2026-07-28T01:22:56.769669Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:56.769669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Donglin Di, Hao Li, Lei Fan, Xuancheng Zhang, Xun Yang, Zhijing Cheng","submitted_at":"2026-07-26T07:20:57Z","abstract_excerpt":"End-to-end autonomous driving systems commonly follow a cascaded two-stage pipeline where a perception stage compresses multi-modal sensor inputs into a compact context and a downstream planner predicts trajectories conditioned on this context. We argue that this one-way perception-to-planning interface forces sensor inputs into a compact representation, losing the fine-grained details critical for planning. Moreover, by constraining the planner to this compressed context, it is difficult to leverage the rich representations offered by modern vision foundation models. To address these issues, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23511","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/2607.23511/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":"2607.23511","created_at":"2026-07-28T01:22:56.770130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23511v1","created_at":"2026-07-28T01:22:56.770130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23511","created_at":"2026-07-28T01:22:56.770130+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQ2PMH6XQA26","created_at":"2026-07-28T01:22:56.770130+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQ2PMH6XQA265G2R","created_at":"2026-07-28T01:22:56.770130+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQ2PMH6X","created_at":"2026-07-28T01:22:56.770130+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/PQ2PMH6XQA265G2RRM7ZQE37ZO","json":"https://pith.science/pith/PQ2PMH6XQA265G2RRM7ZQE37ZO.json","graph_json":"https://pith.science/api/pith-number/PQ2PMH6XQA265G2RRM7ZQE37ZO/graph.json","events_json":"https://pith.science/api/pith-number/PQ2PMH6XQA265G2RRM7ZQE37ZO/events.json","paper":"https://pith.science/paper/PQ2PMH6X"},"agent_actions":{"view_html":"https://pith.science/pith/PQ2PMH6XQA265G2RRM7ZQE37ZO","download_json":"https://pith.science/pith/PQ2PMH6XQA265G2RRM7ZQE37ZO.json","view_paper":"https://pith.science/paper/PQ2PMH6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23511&json=true","fetch_graph":"https://pith.science/api/pith-number/PQ2PMH6XQA265G2RRM7ZQE37ZO/graph.json","fetch_events":"https://pith.science/api/pith-number/PQ2PMH6XQA265G2RRM7ZQE37ZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQ2PMH6XQA265G2RRM7ZQE37ZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQ2PMH6XQA265G2RRM7ZQE37ZO/action/storage_attestation","attest_author":"https://pith.science/pith/PQ2PMH6XQA265G2RRM7ZQE37ZO/action/author_attestation","sign_citation":"https://pith.science/pith/PQ2PMH6XQA265G2RRM7ZQE37ZO/action/citation_signature","submit_replication":"https://pith.science/pith/PQ2PMH6XQA265G2RRM7ZQE37ZO/action/replication_record"}},"created_at":"2026-07-28T01:22:56.770130+00:00","updated_at":"2026-07-28T01:22:56.770130+00:00"}