{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A5BFKJ2DEP57B7LGX6XPK3EFEL","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":"0270c6dd6a70b9654480ced448d39201f3250c21b3a646fcf4ece01fcc738ece","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:40:16Z","title_canon_sha256":"ec205b846d39ab3a4e6bbf271a250b9853f9aed4132d24e4353cc5ce6c8cdb35"},"schema_version":"1.0","source":{"id":"2507.00525","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00525","created_at":"2026-07-05T11:30:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00525v1","created_at":"2026-07-05T11:30:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00525","created_at":"2026-07-05T11:30:10Z"},{"alias_kind":"pith_short_12","alias_value":"A5BFKJ2DEP57","created_at":"2026-07-05T11:30:10Z"},{"alias_kind":"pith_short_16","alias_value":"A5BFKJ2DEP57B7LG","created_at":"2026-07-05T11:30:10Z"},{"alias_kind":"pith_short_8","alias_value":"A5BFKJ2D","created_at":"2026-07-05T11:30:10Z"}],"graph_snapshots":[{"event_id":"sha256:e7be2b9bed3b7c323384adbace04a9d093b1e6b41a8bb5c3c702cffcc87511e4","target":"graph","created_at":"2026-07-05T11:30:10Z","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/2507.00525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Djamahl Etchegaray, Yadan Luo, Yuxia Fu, Zi Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:40:16Z","title":"Box-QAymo: Box-Referring VQA Dataset for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00525","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:f57f52c2bf8fc3146ad2cfd24a7da760a59838ca1b628fb2e535e1df993bb80b","target":"record","created_at":"2026-07-05T11:30:10Z","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":"0270c6dd6a70b9654480ced448d39201f3250c21b3a646fcf4ece01fcc738ece","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:40:16Z","title_canon_sha256":"ec205b846d39ab3a4e6bbf271a250b9853f9aed4132d24e4353cc5ce6c8cdb35"},"schema_version":"1.0","source":{"id":"2507.00525","kind":"arxiv","version":1}},"canonical_sha256":"074255274323fbf0fd66bfaef56c8522f620da5161c4689bb234a98b4c06f2fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"074255274323fbf0fd66bfaef56c8522f620da5161c4689bb234a98b4c06f2fd","first_computed_at":"2026-07-05T11:30:10.326676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:10.326676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dullbn+YbrKAVYimME2IcSKOxaQllhBlQ+nTQyxfVqETNgc9HigDAsiOGU3mY5/5q2xRQ/T7Li0N8k92OpBDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:10.327137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00525","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f57f52c2bf8fc3146ad2cfd24a7da760a59838ca1b628fb2e535e1df993bb80b","sha256:e7be2b9bed3b7c323384adbace04a9d093b1e6b41a8bb5c3c702cffcc87511e4"],"state_sha256":"3d7e4367f89809b0fbdb3b1c63d0fe2b39c71c54ba717ca2f30c1321cab49521"}