{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TCSEX5DPZ4PEHWGE5LJQE2DNLD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b4185658ece4a3f8e1a58342ee37dc1f70a04a1aaf1e754be60c99a2e4153b4c","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-06T03:47:21Z","title_canon_sha256":"d5b55bb810adb7b3e17950fa5dd7461a73844afbff6a18119c23b76c1fd27e19"},"schema_version":"1.0","source":{"id":"2509.05578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05578","created_at":"2026-07-05T12:05:50Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05578v1","created_at":"2026-07-05T12:05:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05578","created_at":"2026-07-05T12:05:50Z"},{"alias_kind":"pith_short_12","alias_value":"TCSEX5DPZ4PE","created_at":"2026-07-05T12:05:50Z"},{"alias_kind":"pith_short_16","alias_value":"TCSEX5DPZ4PEHWGE","created_at":"2026-07-05T12:05:50Z"},{"alias_kind":"pith_short_8","alias_value":"TCSEX5DP","created_at":"2026-07-05T12:05:50Z"}],"graph_snapshots":[{"event_id":"sha256:514fc9e0aa6ad34d113f36fb4e041c4755907a1f464ccd64a8ce9669eeab0578","target":"graph","created_at":"2026-07-05T12:05:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.05578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Derun Li, Hang Zhao, Lingyu Kong, Ruixun Liu","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-06T03:47:21Z","title":"OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05578","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:71ec1a3165452e9ad5c13f649a91e520425aea2fef3fee91f08a8ac1c6a5d6fc","target":"record","created_at":"2026-07-05T12:05:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b4185658ece4a3f8e1a58342ee37dc1f70a04a1aaf1e754be60c99a2e4153b4c","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-06T03:47:21Z","title_canon_sha256":"d5b55bb810adb7b3e17950fa5dd7461a73844afbff6a18119c23b76c1fd27e19"},"schema_version":"1.0","source":{"id":"2509.05578","kind":"arxiv","version":1}},"canonical_sha256":"98a44bf46fcf1e43d8c4ead302686d58f35ae47a5be720613189a04b71ac2fdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98a44bf46fcf1e43d8c4ead302686d58f35ae47a5be720613189a04b71ac2fdb","first_computed_at":"2026-07-05T12:05:50.185221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:50.185221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wWb/o36V1+Jpp0v31XXbbBRaF+VZZDefs6ACXNENlzpV6F/cAjYw+Sf/LoRrRGc/0CKpUpcXbZcnk3dGmngJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:50.185710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71ec1a3165452e9ad5c13f649a91e520425aea2fef3fee91f08a8ac1c6a5d6fc","sha256:514fc9e0aa6ad34d113f36fb4e041c4755907a1f464ccd64a8ce9669eeab0578"],"state_sha256":"ce3c3d9fb68bcfda9c88c9ebe9e57d0ed41d27ef5f39e4b7a84faeb356e79672"}