{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3337B4HRF6AQXNI24MVGIN2MEY","short_pith_number":"pith:3337B4HR","schema_version":"1.0","canonical_sha256":"def7f0f0f12f810bb51ae32a64374c261d89a97cfae05646460e794d0223baac","source":{"kind":"arxiv","id":"2606.20980","version":1},"attestation_state":"computed","paper":{"title":"Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Adrian Cespedes, Arturo Deza, David Ortega, Dunant Cusipuma, Marcelo Chincha, Victor Flores-Benites","submitted_at":"2026-06-18T23:10:36Z","abstract_excerpt":"As Self-Driving Cars continue to expand internationally and use multi-modal systems such as VLMs as a cognitive backbone for their Action models; how well will these systems generalize in new settings, in particular out-of-distribution (OOD) edge-case scenarios in new geographies? In this paper, we study this open question by providing a full factorial analysis with human drivers of Lima, human drivers from New York City, and VLMs and showing them dashcam footage collected from Lima and New York City -- prompting them with a variety of questions under a Visual Question Answering (VQA) paradigm"},"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":"2606.20980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T23:10:36Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"5afb1e3921ea348ab6d675df351fea767d017591f0af60217a12a9570247c468","abstract_canon_sha256":"52f0e878d0de347950963e7abd5b34ff1f676a7955acdb9dfe4c18cae9359e2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:24.223932Z","signature_b64":"r4EdO4n1g7L1Jk8w094KF++hsSEC/PtDvf871hGIOlv1ruE7jXBf6xIArvdFEp2oFdTajra8TB3RXmy9606XDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"def7f0f0f12f810bb51ae32a64374c261d89a97cfae05646460e794d0223baac","last_reissued_at":"2026-06-23T01:12:24.223401Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:24.223401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Adrian Cespedes, Arturo Deza, David Ortega, Dunant Cusipuma, Marcelo Chincha, Victor Flores-Benites","submitted_at":"2026-06-18T23:10:36Z","abstract_excerpt":"As Self-Driving Cars continue to expand internationally and use multi-modal systems such as VLMs as a cognitive backbone for their Action models; how well will these systems generalize in new settings, in particular out-of-distribution (OOD) edge-case scenarios in new geographies? In this paper, we study this open question by providing a full factorial analysis with human drivers of Lima, human drivers from New York City, and VLMs and showing them dashcam footage collected from Lima and New York City -- prompting them with a variety of questions under a Visual Question Answering (VQA) paradigm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20980","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/2606.20980/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":"2606.20980","created_at":"2026-06-23T01:12:24.223482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20980v1","created_at":"2026-06-23T01:12:24.223482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20980","created_at":"2026-06-23T01:12:24.223482+00:00"},{"alias_kind":"pith_short_12","alias_value":"3337B4HRF6AQ","created_at":"2026-06-23T01:12:24.223482+00:00"},{"alias_kind":"pith_short_16","alias_value":"3337B4HRF6AQXNI2","created_at":"2026-06-23T01:12:24.223482+00:00"},{"alias_kind":"pith_short_8","alias_value":"3337B4HR","created_at":"2026-06-23T01:12:24.223482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3337B4HRF6AQXNI24MVGIN2MEY","json":"https://pith.science/pith/3337B4HRF6AQXNI24MVGIN2MEY.json","graph_json":"https://pith.science/api/pith-number/3337B4HRF6AQXNI24MVGIN2MEY/graph.json","events_json":"https://pith.science/api/pith-number/3337B4HRF6AQXNI24MVGIN2MEY/events.json","paper":"https://pith.science/paper/3337B4HR"},"agent_actions":{"view_html":"https://pith.science/pith/3337B4HRF6AQXNI24MVGIN2MEY","download_json":"https://pith.science/pith/3337B4HRF6AQXNI24MVGIN2MEY.json","view_paper":"https://pith.science/paper/3337B4HR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20980&json=true","fetch_graph":"https://pith.science/api/pith-number/3337B4HRF6AQXNI24MVGIN2MEY/graph.json","fetch_events":"https://pith.science/api/pith-number/3337B4HRF6AQXNI24MVGIN2MEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3337B4HRF6AQXNI24MVGIN2MEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3337B4HRF6AQXNI24MVGIN2MEY/action/storage_attestation","attest_author":"https://pith.science/pith/3337B4HRF6AQXNI24MVGIN2MEY/action/author_attestation","sign_citation":"https://pith.science/pith/3337B4HRF6AQXNI24MVGIN2MEY/action/citation_signature","submit_replication":"https://pith.science/pith/3337B4HRF6AQXNI24MVGIN2MEY/action/replication_record"}},"created_at":"2026-06-23T01:12:24.223482+00:00","updated_at":"2026-06-23T01:12:24.223482+00:00"}