{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HIJ5EPJDJ5GPHK2FYCY5W4GXAY","short_pith_number":"pith:HIJ5EPJD","canonical_record":{"source":{"id":"2505.00156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T20:00:37Z","cross_cats_sorted":[],"title_canon_sha256":"45a99e3de0d9c1dc74f9ad0ecd299fea2f47c70b9861c4488620abc97cb5b731","abstract_canon_sha256":"368db9bdfc1facc3aff49f290a699ef828cfdbd1c05ca7fbc3f9c273a1b0aba3"},"schema_version":"1.0"},"canonical_sha256":"3a13d23d234f4cf3ab45c0b1db70d70633d34b251eec0e7b9d4c8b25605ea221","source":{"kind":"arxiv","id":"2505.00156","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00156","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00156v1","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00156","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"pith_short_12","alias_value":"HIJ5EPJDJ5GP","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"pith_short_16","alias_value":"HIJ5EPJDJ5GPHK2F","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"pith_short_8","alias_value":"HIJ5EPJD","created_at":"2026-07-05T10:56:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HIJ5EPJDJ5GPHK2FYCY5W4GXAY","target":"record","payload":{"canonical_record":{"source":{"id":"2505.00156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T20:00:37Z","cross_cats_sorted":[],"title_canon_sha256":"45a99e3de0d9c1dc74f9ad0ecd299fea2f47c70b9861c4488620abc97cb5b731","abstract_canon_sha256":"368db9bdfc1facc3aff49f290a699ef828cfdbd1c05ca7fbc3f9c273a1b0aba3"},"schema_version":"1.0"},"canonical_sha256":"3a13d23d234f4cf3ab45c0b1db70d70633d34b251eec0e7b9d4c8b25605ea221","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:42.630125Z","signature_b64":"P8TlShFAQP+m1epgLvY5moUxcA8pLm4KuonhXuUUNrr0NFOzO38d7RuWZHJ6JGS8gL5Ovj7g4XWw4A9B4ySzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a13d23d234f4cf3ab45c0b1db70d70633d34b251eec0e7b9d4c8b25605ea221","last_reissued_at":"2026-07-05T10:56:42.629584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:42.629584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.00156","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":"2026-07-05T10:56:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2P+zaPEgRNUvSVoTyQ/oNY+vn+CI7FW/5h3pTpqlP4MgKndZIMoTslBh2voa+EX2kYLFqNJe2GCf3H37bK3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:42:07.765253Z"},"content_sha256":"70ca0869da3182bcf1059f0752de4650dd4a5ba57700ef7b2fe22d335ddf9f58","schema_version":"1.0","event_id":"sha256:70ca0869da3182bcf1059f0752de4650dd4a5ba57700ef7b2fe22d335ddf9f58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HIJ5EPJDJ5GPHK2FYCY5W4GXAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"V3LMA: Visual 3D-enhanced Language Model for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Esteban Rivera, Jannik L\\\"ubberstedt, Markus Lienkamp, Nico Uhlemann","submitted_at":"2025-04-30T20:00:37Z","abstract_excerpt":"Large Vision Language Models (LVLMs) have shown strong capabilities in understanding and analyzing visual scenes across various domains. However, in the context of autonomous driving, their limited comprehension of 3D environments restricts their effectiveness in achieving a complete and safe understanding of dynamic surroundings. To address this, we introduce V3LMA, a novel approach that enhances 3D scene understanding by integrating Large Language Models (LLMs) with LVLMs. V3LMA leverages textual descriptions generated from object detections and video inputs, significantly boosting performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00156","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/2505.00156/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":"2026-07-05T10:56:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nfyTtvTNDPouGp6eQvqOTM3cnRqOU4h/+xAVqu9eOFlpwKfRqWsWeyrGrAjID2hbGvM2uQ4o+oDpNAiLKqVhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:42:07.766143Z"},"content_sha256":"d56532e03a7e917415793ed2aee372d88d8f0446353226084754e8244b31ce03","schema_version":"1.0","event_id":"sha256:d56532e03a7e917415793ed2aee372d88d8f0446353226084754e8244b31ce03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HIJ5EPJDJ5GPHK2FYCY5W4GXAY/bundle.json","state_url":"https://pith.science/pith/HIJ5EPJDJ5GPHK2FYCY5W4GXAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HIJ5EPJDJ5GPHK2FYCY5W4GXAY/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":"2026-08-18T02:42:07Z","links":{"resolver":"https://pith.science/pith/HIJ5EPJDJ5GPHK2FYCY5W4GXAY","bundle":"https://pith.science/pith/HIJ5EPJDJ5GPHK2FYCY5W4GXAY/bundle.json","state":"https://pith.science/pith/HIJ5EPJDJ5GPHK2FYCY5W4GXAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HIJ5EPJDJ5GPHK2FYCY5W4GXAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HIJ5EPJDJ5GPHK2FYCY5W4GXAY","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":"368db9bdfc1facc3aff49f290a699ef828cfdbd1c05ca7fbc3f9c273a1b0aba3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T20:00:37Z","title_canon_sha256":"45a99e3de0d9c1dc74f9ad0ecd299fea2f47c70b9861c4488620abc97cb5b731"},"schema_version":"1.0","source":{"id":"2505.00156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00156","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00156v1","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00156","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"pith_short_12","alias_value":"HIJ5EPJDJ5GP","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"pith_short_16","alias_value":"HIJ5EPJDJ5GPHK2F","created_at":"2026-07-05T10:56:42Z"},{"alias_kind":"pith_short_8","alias_value":"HIJ5EPJD","created_at":"2026-07-05T10:56:42Z"}],"graph_snapshots":[{"event_id":"sha256:d56532e03a7e917415793ed2aee372d88d8f0446353226084754e8244b31ce03","target":"graph","created_at":"2026-07-05T10:56:42Z","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/2505.00156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision Language Models (LVLMs) have shown strong capabilities in understanding and analyzing visual scenes across various domains. However, in the context of autonomous driving, their limited comprehension of 3D environments restricts their effectiveness in achieving a complete and safe understanding of dynamic surroundings. To address this, we introduce V3LMA, a novel approach that enhances 3D scene understanding by integrating Large Language Models (LLMs) with LVLMs. V3LMA leverages textual descriptions generated from object detections and video inputs, significantly boosting performan","authors_text":"Esteban Rivera, Jannik L\\\"ubberstedt, Markus Lienkamp, Nico Uhlemann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T20:00:37Z","title":"V3LMA: Visual 3D-enhanced Language Model for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00156","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":"sha256:70ca0869da3182bcf1059f0752de4650dd4a5ba57700ef7b2fe22d335ddf9f58","target":"record","created_at":"2026-07-05T10:56:42Z","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":"368db9bdfc1facc3aff49f290a699ef828cfdbd1c05ca7fbc3f9c273a1b0aba3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T20:00:37Z","title_canon_sha256":"45a99e3de0d9c1dc74f9ad0ecd299fea2f47c70b9861c4488620abc97cb5b731"},"schema_version":"1.0","source":{"id":"2505.00156","kind":"arxiv","version":1}},"canonical_sha256":"3a13d23d234f4cf3ab45c0b1db70d70633d34b251eec0e7b9d4c8b25605ea221","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a13d23d234f4cf3ab45c0b1db70d70633d34b251eec0e7b9d4c8b25605ea221","first_computed_at":"2026-07-05T10:56:42.629584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:42.629584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P8TlShFAQP+m1epgLvY5moUxcA8pLm4KuonhXuUUNrr0NFOzO38d7RuWZHJ6JGS8gL5Ovj7g4XWw4A9B4ySzBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:42.630125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70ca0869da3182bcf1059f0752de4650dd4a5ba57700ef7b2fe22d335ddf9f58","sha256:d56532e03a7e917415793ed2aee372d88d8f0446353226084754e8244b31ce03"],"state_sha256":"f07ce3302ad707a9903e1f22b3dcdba9024033f90e8a5d289ba4604b090f2384"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d3/tjMu2jojTZqooQ6Bi4IvXa0Pl23F5M2Ii9kssjurgxTRLbblgukbJl2PDL1QE7nJShItpM6gdtWg3cymMBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T02:42:07.863169Z","bundle_sha256":"b95b737fa74e4acad05f9488516aaa18fb0caa30a909185b95e825f1886df0ff"}}