{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GVQQEZRSIIFHM5SI6TRMZF2WLY","short_pith_number":"pith:GVQQEZRS","canonical_record":{"source":{"id":"2605.22089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T07:31:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9bd1eb454679a624ec7029684fb29e6bf195122f4973ee4a97a940bb55726f93","abstract_canon_sha256":"cd10804f1ccdd1c2ff44b9394447d8376638aa6facb51bdff66cf70be0074152"},"schema_version":"1.0"},"canonical_sha256":"3561026632420a767648f4e2cc97565e0c4f48563fe3e44416c8d0d9c9a31263","source":{"kind":"arxiv","id":"2605.22089","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22089","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22089v1","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22089","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"GVQQEZRSIIFH","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"GVQQEZRSIIFHM5SI","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"GVQQEZRS","created_at":"2026-05-22T01:04:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GVQQEZRSIIFHM5SI6TRMZF2WLY","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T07:31:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9bd1eb454679a624ec7029684fb29e6bf195122f4973ee4a97a940bb55726f93","abstract_canon_sha256":"cd10804f1ccdd1c2ff44b9394447d8376638aa6facb51bdff66cf70be0074152"},"schema_version":"1.0"},"canonical_sha256":"3561026632420a767648f4e2cc97565e0c4f48563fe3e44416c8d0d9c9a31263","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:25.066401Z","signature_b64":"nBeM0XYzA5BySnld5x3Ui9ympHo3FfWm9FpPLXyFPBGlKqJUqbxl+yfSre+lZsndi1vh6vkVk2coZnF90DNGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3561026632420a767648f4e2cc97565e0c4f48563fe3e44416c8d0d9c9a31263","last_reissued_at":"2026-05-22T01:04:25.065584Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:25.065584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22089","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y1lzbvyJQIThI1EA/TUUXATtFWsFbmN2LO6ZZ4+j6I7Wl+DdvcCf/V089xT2rcd1GvqoWN1ybkrrPCk+x5eLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T13:03:37.066999Z"},"content_sha256":"ffcef6a6afdc3ebf1da3d86979546a89f1ffb83b8553a97c368375df273034d0","schema_version":"1.0","event_id":"sha256:ffcef6a6afdc3ebf1da3d86979546a89f1ffb83b8553a97c368375df273034d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GVQQEZRSIIFHM5SI6TRMZF2WLY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dan Xu, Diankun Zhang, Guang Chen, Hangjun Ye, Hongwei Xie, Xiaodong Mei","submitted_at":"2026-05-21T07:31:49Z","abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sparse action supervision, which underutilizes their powerful scene understanding and reasoning capabilities. Recent attempts to incorporate dense visual supervision via world modeling often overemphasize pixel-level image reconstruction, neglecting semantically meaningful scene representation learning. In this work, we propose LVDrive, a Latent Visual representation enhanced VLA framework for autonomous driving. LVDrive introduces a future scene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22089","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/2605.22089/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aaoXfl9GNuJGYcdmrkdQW7QO0YJBAGbxBVn8FTfUgxDt+3kRcdfTbyvo1/FPZ7XdUkLnGlYjJ376m7oyLd/3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T13:03:37.067534Z"},"content_sha256":"42e8d6cf7ebd643040f5521754c15333834dc31bc5cc3d3c97ee752a5f466a23","schema_version":"1.0","event_id":"sha256:42e8d6cf7ebd643040f5521754c15333834dc31bc5cc3d3c97ee752a5f466a23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVQQEZRSIIFHM5SI6TRMZF2WLY/bundle.json","state_url":"https://pith.science/pith/GVQQEZRSIIFHM5SI6TRMZF2WLY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVQQEZRSIIFHM5SI6TRMZF2WLY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T13:03:37Z","links":{"resolver":"https://pith.science/pith/GVQQEZRSIIFHM5SI6TRMZF2WLY","bundle":"https://pith.science/pith/GVQQEZRSIIFHM5SI6TRMZF2WLY/bundle.json","state":"https://pith.science/pith/GVQQEZRSIIFHM5SI6TRMZF2WLY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVQQEZRSIIFHM5SI6TRMZF2WLY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GVQQEZRSIIFHM5SI6TRMZF2WLY","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":"cd10804f1ccdd1c2ff44b9394447d8376638aa6facb51bdff66cf70be0074152","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T07:31:49Z","title_canon_sha256":"9bd1eb454679a624ec7029684fb29e6bf195122f4973ee4a97a940bb55726f93"},"schema_version":"1.0","source":{"id":"2605.22089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22089","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22089v1","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22089","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"GVQQEZRSIIFH","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"GVQQEZRSIIFHM5SI","created_at":"2026-05-22T01:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"GVQQEZRS","created_at":"2026-05-22T01:04:25Z"}],"graph_snapshots":[{"event_id":"sha256:42e8d6cf7ebd643040f5521754c15333834dc31bc5cc3d3c97ee752a5f466a23","target":"graph","created_at":"2026-05-22T01:04:25Z","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/2605.22089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sparse action supervision, which underutilizes their powerful scene understanding and reasoning capabilities. Recent attempts to incorporate dense visual supervision via world modeling often overemphasize pixel-level image reconstruction, neglecting semantically meaningful scene representation learning. In this work, we propose LVDrive, a Latent Visual representation enhanced VLA framework for autonomous driving. LVDrive introduces a future scene","authors_text":"Dan Xu, Diankun Zhang, Guang Chen, Hangjun Ye, Hongwei Xie, Xiaodong Mei","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T07:31:49Z","title":"LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22089","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:ffcef6a6afdc3ebf1da3d86979546a89f1ffb83b8553a97c368375df273034d0","target":"record","created_at":"2026-05-22T01:04:25Z","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":"cd10804f1ccdd1c2ff44b9394447d8376638aa6facb51bdff66cf70be0074152","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T07:31:49Z","title_canon_sha256":"9bd1eb454679a624ec7029684fb29e6bf195122f4973ee4a97a940bb55726f93"},"schema_version":"1.0","source":{"id":"2605.22089","kind":"arxiv","version":1}},"canonical_sha256":"3561026632420a767648f4e2cc97565e0c4f48563fe3e44416c8d0d9c9a31263","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3561026632420a767648f4e2cc97565e0c4f48563fe3e44416c8d0d9c9a31263","first_computed_at":"2026-05-22T01:04:25.065584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:25.065584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nBeM0XYzA5BySnld5x3Ui9ympHo3FfWm9FpPLXyFPBGlKqJUqbxl+yfSre+lZsndi1vh6vkVk2coZnF90DNGAA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:25.066401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffcef6a6afdc3ebf1da3d86979546a89f1ffb83b8553a97c368375df273034d0","sha256:42e8d6cf7ebd643040f5521754c15333834dc31bc5cc3d3c97ee752a5f466a23"],"state_sha256":"4f24ca20c2e04197a515d7ea8c0d8772d7649e51015b985cff2d1ebf500978cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8r7sQQRCbPo8nhLiHYmTEK5OwIax21u9/YE0KvwpEJxpfW1JBAVjNw1kUdDzawFE6OMhp0AtuT3QqGHDjF+Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T13:03:37.070611Z","bundle_sha256":"22dcec1019435b7f5c551f395f5f5bb5d5ae6e349296983934df2032a5c4d8b1"}}