{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A5BFKJ2DEP57B7LGX6XPK3EFEL","short_pith_number":"pith:A5BFKJ2D","schema_version":"1.0","canonical_sha256":"074255274323fbf0fd66bfaef56c8522f620da5161c4689bb234a98b4c06f2fd","source":{"kind":"arxiv","id":"2507.00525","version":1},"attestation_state":"computed","paper":{"title":"Box-QAymo: Box-Referring VQA Dataset for Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Djamahl Etchegaray, Yadan Luo, Yuxia Fu, Zi Huang","submitted_at":"2025-07-01T07:40:16Z","abstract_excerpt":"Interpretable communication is essential for safe and trustworthy autonomous driving, yet current vision-language models (VLMs) often operate under idealized assumptions and struggle to capture user intent in real-world scenarios. Existing driving-oriented VQA datasets are limited to full-scene descriptions or waypoint prediction, preventing the assessment of whether VLMs can respond to localized user-driven queries. We introduce Box-QAymo, a box-referring dataset and benchmark designed to both evaluate and finetune VLMs on spatial and temporal reasoning over user-specified objects. Users expr"},"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":"2507.00525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:40:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec205b846d39ab3a4e6bbf271a250b9853f9aed4132d24e4353cc5ce6c8cdb35","abstract_canon_sha256":"0270c6dd6a70b9654480ced448d39201f3250c21b3a646fcf4ece01fcc738ece"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:10.327137Z","signature_b64":"Dullbn+YbrKAVYimME2IcSKOxaQllhBlQ+nTQyxfVqETNgc9HigDAsiOGU3mY5/5q2xRQ/T7Li0N8k92OpBDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"074255274323fbf0fd66bfaef56c8522f620da5161c4689bb234a98b4c06f2fd","last_reissued_at":"2026-07-05T11:30:10.326676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:10.326676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Box-QAymo: Box-Referring VQA Dataset for Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Djamahl Etchegaray, Yadan Luo, Yuxia Fu, Zi Huang","submitted_at":"2025-07-01T07:40:16Z","abstract_excerpt":"Interpretable communication is essential for safe and trustworthy autonomous driving, yet current vision-language models (VLMs) often operate under idealized assumptions and struggle to capture user intent in real-world scenarios. Existing driving-oriented VQA datasets are limited to full-scene descriptions or waypoint prediction, preventing the assessment of whether VLMs can respond to localized user-driven queries. We introduce Box-QAymo, a box-referring dataset and benchmark designed to both evaluate and finetune VLMs on spatial and temporal reasoning over user-specified objects. Users expr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00525","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/2507.00525/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":"2507.00525","created_at":"2026-07-05T11:30:10.326734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00525v1","created_at":"2026-07-05T11:30:10.326734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00525","created_at":"2026-07-05T11:30:10.326734+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5BFKJ2DEP57","created_at":"2026-07-05T11:30:10.326734+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5BFKJ2DEP57B7LG","created_at":"2026-07-05T11:30:10.326734+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5BFKJ2D","created_at":"2026-07-05T11:30:10.326734+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/A5BFKJ2DEP57B7LGX6XPK3EFEL","json":"https://pith.science/pith/A5BFKJ2DEP57B7LGX6XPK3EFEL.json","graph_json":"https://pith.science/api/pith-number/A5BFKJ2DEP57B7LGX6XPK3EFEL/graph.json","events_json":"https://pith.science/api/pith-number/A5BFKJ2DEP57B7LGX6XPK3EFEL/events.json","paper":"https://pith.science/paper/A5BFKJ2D"},"agent_actions":{"view_html":"https://pith.science/pith/A5BFKJ2DEP57B7LGX6XPK3EFEL","download_json":"https://pith.science/pith/A5BFKJ2DEP57B7LGX6XPK3EFEL.json","view_paper":"https://pith.science/paper/A5BFKJ2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00525&json=true","fetch_graph":"https://pith.science/api/pith-number/A5BFKJ2DEP57B7LGX6XPK3EFEL/graph.json","fetch_events":"https://pith.science/api/pith-number/A5BFKJ2DEP57B7LGX6XPK3EFEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5BFKJ2DEP57B7LGX6XPK3EFEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5BFKJ2DEP57B7LGX6XPK3EFEL/action/storage_attestation","attest_author":"https://pith.science/pith/A5BFKJ2DEP57B7LGX6XPK3EFEL/action/author_attestation","sign_citation":"https://pith.science/pith/A5BFKJ2DEP57B7LGX6XPK3EFEL/action/citation_signature","submit_replication":"https://pith.science/pith/A5BFKJ2DEP57B7LGX6XPK3EFEL/action/replication_record"}},"created_at":"2026-07-05T11:30:10.326734+00:00","updated_at":"2026-07-05T11:30:10.326734+00:00"}