{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:O4WOXUVT7PM74ZEI4Q23WZLYVF","short_pith_number":"pith:O4WOXUVT","canonical_record":{"source":{"id":"2605.21747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T21:17:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"bb0c92ff2876e4a1b803d387a939a097f5faa60dabc2f2c0db76ab76dacc8f9c","abstract_canon_sha256":"7bff052fb2643da0ea427876147b4e89eb79ce29f90a9e7bb773e4331299acb5"},"schema_version":"1.0"},"canonical_sha256":"772cebd2b3fbd9fe6488e435bb6578a971fe0cc461b3dcb98ad9a1c418cf3684","source":{"kind":"arxiv","id":"2605.21747","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21747","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21747v1","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21747","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"O4WOXUVT7PM7","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"O4WOXUVT7PM74ZEI","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"O4WOXUVT","created_at":"2026-05-22T01:03:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:O4WOXUVT7PM74ZEI4Q23WZLYVF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T21:17:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"bb0c92ff2876e4a1b803d387a939a097f5faa60dabc2f2c0db76ab76dacc8f9c","abstract_canon_sha256":"7bff052fb2643da0ea427876147b4e89eb79ce29f90a9e7bb773e4331299acb5"},"schema_version":"1.0"},"canonical_sha256":"772cebd2b3fbd9fe6488e435bb6578a971fe0cc461b3dcb98ad9a1c418cf3684","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:30.378871Z","signature_b64":"vtw7zYacOItxpRFz7A9fA0GkGackfPUXLBxiK4gyhRk1lgbESgwtWJnoO18CgDvMb4ET+jNpX40jmpYFdvSaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"772cebd2b3fbd9fe6488e435bb6578a971fe0cc461b3dcb98ad9a1c418cf3684","last_reissued_at":"2026-05-22T01:03:30.378411Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:30.378411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21747","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":"2026-05-22T01:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cltcR+F1T6XKL+376eP1Acr4x3UCwG6D13nV1H3MFXxxcvqAqTfD5TDI6TkLNdOg6p47ab7TEjPpCL0HowAyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:31:46.761472Z"},"content_sha256":"ca16dd38547b3b4888380bb8aa4909fce6d475fd343252f3f72ddd7194aa11c5","schema_version":"1.0","event_id":"sha256:ca16dd38547b3b4888380bb8aa4909fce6d475fd343252f3f72ddd7194aa11c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:O4WOXUVT7PM74ZEI4Q23WZLYVF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving 3D Labeling in Self-Driving by Inferring Vehicle Information using Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Nemanja Djuric, Shivesh Khaitan, Steven Chen","submitted_at":"2026-05-20T21:17:57Z","abstract_excerpt":"We present an approach to improve 3D vehicle labeling in self-driving applications through zero-shot inference of vehicle information, leveraging Vehicle Make and Model Recognition (VMMR) methods. The proposed approach utilizes a Vision Language Model (VLM) to both infer a vehicle's make, model, and generation from image crops, and output accurate 3D bounding box dimensions to seed manual labeling. We evaluate the impact of iterative prompt engineering and the choice of different VLMs on both vehicle bounding box inference and make/model/generation recognition. When compared to strong baseline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21747","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/2605.21747/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":"2026-05-22T01:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mI4vp6yWiis6QZHM3gjHQZJkXSvzK/SLS7vcqef3Mdkzt9VuhCZpRg//CuoL5gh7ieRKAcR/ey41kIroP9mADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:31:46.761898Z"},"content_sha256":"5f229f47c2e8c6afa01e83a8b8f5aa16575675f396af089e0aaf59cfb6d34092","schema_version":"1.0","event_id":"sha256:5f229f47c2e8c6afa01e83a8b8f5aa16575675f396af089e0aaf59cfb6d34092"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4WOXUVT7PM74ZEI4Q23WZLYVF/bundle.json","state_url":"https://pith.science/pith/O4WOXUVT7PM74ZEI4Q23WZLYVF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4WOXUVT7PM74ZEI4Q23WZLYVF/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":"2026-06-10T13:31:46Z","links":{"resolver":"https://pith.science/pith/O4WOXUVT7PM74ZEI4Q23WZLYVF","bundle":"https://pith.science/pith/O4WOXUVT7PM74ZEI4Q23WZLYVF/bundle.json","state":"https://pith.science/pith/O4WOXUVT7PM74ZEI4Q23WZLYVF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4WOXUVT7PM74ZEI4Q23WZLYVF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O4WOXUVT7PM74ZEI4Q23WZLYVF","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":"7bff052fb2643da0ea427876147b4e89eb79ce29f90a9e7bb773e4331299acb5","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T21:17:57Z","title_canon_sha256":"bb0c92ff2876e4a1b803d387a939a097f5faa60dabc2f2c0db76ab76dacc8f9c"},"schema_version":"1.0","source":{"id":"2605.21747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21747","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21747v1","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21747","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"O4WOXUVT7PM7","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"O4WOXUVT7PM74ZEI","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"O4WOXUVT","created_at":"2026-05-22T01:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:5f229f47c2e8c6afa01e83a8b8f5aa16575675f396af089e0aaf59cfb6d34092","target":"graph","created_at":"2026-05-22T01:03:30Z","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/2605.21747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an approach to improve 3D vehicle labeling in self-driving applications through zero-shot inference of vehicle information, leveraging Vehicle Make and Model Recognition (VMMR) methods. The proposed approach utilizes a Vision Language Model (VLM) to both infer a vehicle's make, model, and generation from image crops, and output accurate 3D bounding box dimensions to seed manual labeling. We evaluate the impact of iterative prompt engineering and the choice of different VLMs on both vehicle bounding box inference and make/model/generation recognition. When compared to strong baseline","authors_text":"Nemanja Djuric, Shivesh Khaitan, Steven Chen","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T21:17:57Z","title":"Improving 3D Labeling in Self-Driving by Inferring Vehicle Information using Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21747","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:ca16dd38547b3b4888380bb8aa4909fce6d475fd343252f3f72ddd7194aa11c5","target":"record","created_at":"2026-05-22T01:03:30Z","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":"7bff052fb2643da0ea427876147b4e89eb79ce29f90a9e7bb773e4331299acb5","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T21:17:57Z","title_canon_sha256":"bb0c92ff2876e4a1b803d387a939a097f5faa60dabc2f2c0db76ab76dacc8f9c"},"schema_version":"1.0","source":{"id":"2605.21747","kind":"arxiv","version":1}},"canonical_sha256":"772cebd2b3fbd9fe6488e435bb6578a971fe0cc461b3dcb98ad9a1c418cf3684","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"772cebd2b3fbd9fe6488e435bb6578a971fe0cc461b3dcb98ad9a1c418cf3684","first_computed_at":"2026-05-22T01:03:30.378411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:30.378411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vtw7zYacOItxpRFz7A9fA0GkGackfPUXLBxiK4gyhRk1lgbESgwtWJnoO18CgDvMb4ET+jNpX40jmpYFdvSaAA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:30.378871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca16dd38547b3b4888380bb8aa4909fce6d475fd343252f3f72ddd7194aa11c5","sha256:5f229f47c2e8c6afa01e83a8b8f5aa16575675f396af089e0aaf59cfb6d34092"],"state_sha256":"4d979722f0da66a900f8202a867632044d6eeba66aedf17e3baecb63205af427"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ufAj8E4kZXXHOVuwv7c2VIpgdhb5J6rQXzyupwqX+dqHM6vLcRAhZw2Z/R9QhGd/l9/dJf9unB9BRSqRCRqBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T13:31:46.764670Z","bundle_sha256":"f0cba88c5d96a169d783a749713feb7166efdc128e27814953f3692a6e1f0398"}}