{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VLKXXIN2DYSTDQQ2222FRU56SK","short_pith_number":"pith:VLKXXIN2","schema_version":"1.0","canonical_sha256":"aad57ba1ba1e2531c21ad6b458d3be92972d62911505d086370a1c4b897a820d","source":{"kind":"arxiv","id":"2502.06419","version":1},"attestation_state":"computed","paper":{"title":"Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bingbing Liu, Hao Lu, Tianshuo Xu, Xu Yan, Yingcong Chen, Yingjie Cai","submitted_at":"2025-02-10T12:55:21Z","abstract_excerpt":"Large Language Models (LLMs) have made substantial advancements in the field of robotic and autonomous driving. This study presents the first Occupancy-based Large Language Model (Occ-LLM), which represents a pioneering effort to integrate LLMs with an important representation. To effectively encode occupancy as input for the LLM and address the category imbalances associated with occupancy, we propose Motion Separation Variational Autoencoder (MS-VAE). This innovative approach utilizes prior knowledge to distinguish dynamic objects from static scenes before inputting them into a tailored Vari"},"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":"2502.06419","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-02-10T12:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"50b572f0c572fe24d5c1e4855fc70e9fa2678cd44edf27eba764bcbc4933d1d3","abstract_canon_sha256":"92aafb8f80dc8cff3b01d6cd0c3431f1fc5ba130b2b5e96f6314905d5bb01403"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:06.256336Z","signature_b64":"qvN8agOoYzn/yEjTk7C/inbeW+WYei+uT1GfKPLXV7HB0cjl5LchSuGb2d/HpsznBL79NtqKkr1yI45qbjiuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aad57ba1ba1e2531c21ad6b458d3be92972d62911505d086370a1c4b897a820d","last_reissued_at":"2026-07-05T10:12:06.255471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:06.255471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bingbing Liu, Hao Lu, Tianshuo Xu, Xu Yan, Yingcong Chen, Yingjie Cai","submitted_at":"2025-02-10T12:55:21Z","abstract_excerpt":"Large Language Models (LLMs) have made substantial advancements in the field of robotic and autonomous driving. This study presents the first Occupancy-based Large Language Model (Occ-LLM), which represents a pioneering effort to integrate LLMs with an important representation. To effectively encode occupancy as input for the LLM and address the category imbalances associated with occupancy, we propose Motion Separation Variational Autoencoder (MS-VAE). This innovative approach utilizes prior knowledge to distinguish dynamic objects from static scenes before inputting them into a tailored Vari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06419","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/2502.06419/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":"2502.06419","created_at":"2026-07-05T10:12:06.255535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06419v1","created_at":"2026-07-05T10:12:06.255535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06419","created_at":"2026-07-05T10:12:06.255535+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLKXXIN2DYST","created_at":"2026-07-05T10:12:06.255535+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLKXXIN2DYSTDQQ2","created_at":"2026-07-05T10:12:06.255535+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLKXXIN2","created_at":"2026-07-05T10:12:06.255535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27644","citing_title":"CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30421","citing_title":"OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22039","citing_title":"SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28196","citing_title":"HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09059","citing_title":"Learning Vision-Language-Action World Models for Autonomous Driving","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLKXXIN2DYSTDQQ2222FRU56SK","json":"https://pith.science/pith/VLKXXIN2DYSTDQQ2222FRU56SK.json","graph_json":"https://pith.science/api/pith-number/VLKXXIN2DYSTDQQ2222FRU56SK/graph.json","events_json":"https://pith.science/api/pith-number/VLKXXIN2DYSTDQQ2222FRU56SK/events.json","paper":"https://pith.science/paper/VLKXXIN2"},"agent_actions":{"view_html":"https://pith.science/pith/VLKXXIN2DYSTDQQ2222FRU56SK","download_json":"https://pith.science/pith/VLKXXIN2DYSTDQQ2222FRU56SK.json","view_paper":"https://pith.science/paper/VLKXXIN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06419&json=true","fetch_graph":"https://pith.science/api/pith-number/VLKXXIN2DYSTDQQ2222FRU56SK/graph.json","fetch_events":"https://pith.science/api/pith-number/VLKXXIN2DYSTDQQ2222FRU56SK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLKXXIN2DYSTDQQ2222FRU56SK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLKXXIN2DYSTDQQ2222FRU56SK/action/storage_attestation","attest_author":"https://pith.science/pith/VLKXXIN2DYSTDQQ2222FRU56SK/action/author_attestation","sign_citation":"https://pith.science/pith/VLKXXIN2DYSTDQQ2222FRU56SK/action/citation_signature","submit_replication":"https://pith.science/pith/VLKXXIN2DYSTDQQ2222FRU56SK/action/replication_record"}},"created_at":"2026-07-05T10:12:06.255535+00:00","updated_at":"2026-07-05T10:12:06.255535+00:00"}