{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TCSEX5DPZ4PEHWGE5LJQE2DNLD","short_pith_number":"pith:TCSEX5DP","schema_version":"1.0","canonical_sha256":"98a44bf46fcf1e43d8c4ead302686d58f35ae47a5be720613189a04b71ac2fdb","source":{"kind":"arxiv","id":"2509.05578","version":1},"attestation_state":"computed","paper":{"title":"OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Derun Li, Hang Zhao, Lingyu Kong, Ruixun Liu","submitted_at":"2025-09-06T03:47:21Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown strong vision-language reasoning abilities but still lack robust 3D spatial understanding, which is critical for autonomous driving. This limitation stems from two key challenges: (1) the difficulty of constructing accessible yet effective 3D representations without expensive manual annotations, and (2) the loss of fine-grained spatial details in VLMs due to the absence of large-scale 3D vision-language pretraining. To address these challenges, we propose OccVLA, a novel framework that integrates 3D occupancy representations into a unified mu"},"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":"2509.05578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-06T03:47:21Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"d5b55bb810adb7b3e17950fa5dd7461a73844afbff6a18119c23b76c1fd27e19","abstract_canon_sha256":"b4185658ece4a3f8e1a58342ee37dc1f70a04a1aaf1e754be60c99a2e4153b4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:50.185710Z","signature_b64":"wWb/o36V1+Jpp0v31XXbbBRaF+VZZDefs6ACXNENlzpV6F/cAjYw+Sf/LoRrRGc/0CKpUpcXbZcnk3dGmngJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98a44bf46fcf1e43d8c4ead302686d58f35ae47a5be720613189a04b71ac2fdb","last_reissued_at":"2026-07-05T12:05:50.185221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:50.185221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Derun Li, Hang Zhao, Lingyu Kong, Ruixun Liu","submitted_at":"2025-09-06T03:47:21Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown strong vision-language reasoning abilities but still lack robust 3D spatial understanding, which is critical for autonomous driving. This limitation stems from two key challenges: (1) the difficulty of constructing accessible yet effective 3D representations without expensive manual annotations, and (2) the loss of fine-grained spatial details in VLMs due to the absence of large-scale 3D vision-language pretraining. To address these challenges, we propose OccVLA, a novel framework that integrates 3D occupancy representations into a unified mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05578","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/2509.05578/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":"2509.05578","created_at":"2026-07-05T12:05:50.185281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05578v1","created_at":"2026-07-05T12:05:50.185281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05578","created_at":"2026-07-05T12:05:50.185281+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCSEX5DPZ4PE","created_at":"2026-07-05T12:05:50.185281+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCSEX5DPZ4PEHWGE","created_at":"2026-07-05T12:05:50.185281+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCSEX5DP","created_at":"2026-07-05T12:05:50.185281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01658","citing_title":"Teaching Vision-Language-Action Models What to See and Where to Look","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05008","citing_title":"M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27038","citing_title":"TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22667","citing_title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03370","citing_title":"ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05072","citing_title":"Height-Guided Projection Reparameterization for Camera-LiDAR Occupancy","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05072","citing_title":"Height-Guided Projection Reparameterization for Camera-LiDAR Occupancy","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TCSEX5DPZ4PEHWGE5LJQE2DNLD","json":"https://pith.science/pith/TCSEX5DPZ4PEHWGE5LJQE2DNLD.json","graph_json":"https://pith.science/api/pith-number/TCSEX5DPZ4PEHWGE5LJQE2DNLD/graph.json","events_json":"https://pith.science/api/pith-number/TCSEX5DPZ4PEHWGE5LJQE2DNLD/events.json","paper":"https://pith.science/paper/TCSEX5DP"},"agent_actions":{"view_html":"https://pith.science/pith/TCSEX5DPZ4PEHWGE5LJQE2DNLD","download_json":"https://pith.science/pith/TCSEX5DPZ4PEHWGE5LJQE2DNLD.json","view_paper":"https://pith.science/paper/TCSEX5DP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05578&json=true","fetch_graph":"https://pith.science/api/pith-number/TCSEX5DPZ4PEHWGE5LJQE2DNLD/graph.json","fetch_events":"https://pith.science/api/pith-number/TCSEX5DPZ4PEHWGE5LJQE2DNLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCSEX5DPZ4PEHWGE5LJQE2DNLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCSEX5DPZ4PEHWGE5LJQE2DNLD/action/storage_attestation","attest_author":"https://pith.science/pith/TCSEX5DPZ4PEHWGE5LJQE2DNLD/action/author_attestation","sign_citation":"https://pith.science/pith/TCSEX5DPZ4PEHWGE5LJQE2DNLD/action/citation_signature","submit_replication":"https://pith.science/pith/TCSEX5DPZ4PEHWGE5LJQE2DNLD/action/replication_record"}},"created_at":"2026-07-05T12:05:50.185281+00:00","updated_at":"2026-07-05T12:05:50.185281+00:00"}