{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XCHNCOG36TXXGIF2LA6W7JIBLY","short_pith_number":"pith:XCHNCOG3","schema_version":"1.0","canonical_sha256":"b88ed138dbf4ef7320ba583d6fa5015e280b9f0d28aa957c49a6f651d1c76dbf","source":{"kind":"arxiv","id":"2508.02047","version":1},"attestation_state":"computed","paper":{"title":"Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Aich, Sparsh Garg","submitted_at":"2025-08-04T04:29:06Z","abstract_excerpt":"Obtaining high-quality fine-grained annotations for traffic signs is critical for accurate and safe decision-making in autonomous driving. Widely used datasets, such as Mapillary, often provide only coarse-grained labels - without distinguishing semantically important types such as stop signs or speed limit signs. To this end, we present a new validation set for traffic signs derived from the Mapillary dataset called Mapillary Vistas Validation for Traffic Signs (MVV), where we decompose composite traffic signs into granular, semantically meaningful categories. The dataset includes pixel-level"},"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":"2508.02047","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-04T04:29:06Z","cross_cats_sorted":[],"title_canon_sha256":"b775e5eb662957cff91f6c12459d2e77f7f19cfcc7d62cbca1ce4fa100ddf576","abstract_canon_sha256":"9c0b2cbcfb7afd4a6bece2a361907d897588f8f179bac374d2676775e6e3acd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:50.064443Z","signature_b64":"CLkiLkKR1nzX7nSMO6ON9M560YSGUVTMxtsBmBbCq/SKoa529h3jfmnGU1h9Tj0Fxik8DgG43IZskDzRvmiVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b88ed138dbf4ef7320ba583d6fa5015e280b9f0d28aa957c49a6f651d1c76dbf","last_reissued_at":"2026-07-05T11:47:50.064075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:50.064075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Aich, Sparsh Garg","submitted_at":"2025-08-04T04:29:06Z","abstract_excerpt":"Obtaining high-quality fine-grained annotations for traffic signs is critical for accurate and safe decision-making in autonomous driving. Widely used datasets, such as Mapillary, often provide only coarse-grained labels - without distinguishing semantically important types such as stop signs or speed limit signs. To this end, we present a new validation set for traffic signs derived from the Mapillary dataset called Mapillary Vistas Validation for Traffic Signs (MVV), where we decompose composite traffic signs into granular, semantically meaningful categories. The dataset includes pixel-level"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02047","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/2508.02047/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":"2508.02047","created_at":"2026-07-05T11:47:50.064146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02047v1","created_at":"2026-07-05T11:47:50.064146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02047","created_at":"2026-07-05T11:47:50.064146+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCHNCOG36TXX","created_at":"2026-07-05T11:47:50.064146+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCHNCOG36TXXGIF2","created_at":"2026-07-05T11:47:50.064146+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCHNCOG3","created_at":"2026-07-05T11:47:50.064146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06560","citing_title":"Vision as Unified Multimodal Generation","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCHNCOG36TXXGIF2LA6W7JIBLY","json":"https://pith.science/pith/XCHNCOG36TXXGIF2LA6W7JIBLY.json","graph_json":"https://pith.science/api/pith-number/XCHNCOG36TXXGIF2LA6W7JIBLY/graph.json","events_json":"https://pith.science/api/pith-number/XCHNCOG36TXXGIF2LA6W7JIBLY/events.json","paper":"https://pith.science/paper/XCHNCOG3"},"agent_actions":{"view_html":"https://pith.science/pith/XCHNCOG36TXXGIF2LA6W7JIBLY","download_json":"https://pith.science/pith/XCHNCOG36TXXGIF2LA6W7JIBLY.json","view_paper":"https://pith.science/paper/XCHNCOG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02047&json=true","fetch_graph":"https://pith.science/api/pith-number/XCHNCOG36TXXGIF2LA6W7JIBLY/graph.json","fetch_events":"https://pith.science/api/pith-number/XCHNCOG36TXXGIF2LA6W7JIBLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCHNCOG36TXXGIF2LA6W7JIBLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCHNCOG36TXXGIF2LA6W7JIBLY/action/storage_attestation","attest_author":"https://pith.science/pith/XCHNCOG36TXXGIF2LA6W7JIBLY/action/author_attestation","sign_citation":"https://pith.science/pith/XCHNCOG36TXXGIF2LA6W7JIBLY/action/citation_signature","submit_replication":"https://pith.science/pith/XCHNCOG36TXXGIF2LA6W7JIBLY/action/replication_record"}},"created_at":"2026-07-05T11:47:50.064146+00:00","updated_at":"2026-07-05T11:47:50.064146+00:00"}