{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H6CZM6LMFDXD2XBSDP5EDRBJ5U","short_pith_number":"pith:H6CZM6LM","schema_version":"1.0","canonical_sha256":"3f8596796c28ee3d5c321bfa41c429ed2cf2357b8405343e631ec596dd87ebc9","source":{"kind":"arxiv","id":"2501.17131","version":2},"attestation_state":"computed","paper":{"title":"Scenario Understanding of Traffic Scenes Through Large Visual Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Esteban Rivera, Jannik L\\\"ubberstedt, Markus Lienkamp, Nico Uhlemann","submitted_at":"2025-01-28T18:23:12Z","abstract_excerpt":"Deep learning models for autonomous driving, encompassing perception, planning, and control, depend on vast datasets to achieve their high performance. However, their generalization often suffers due to domain-specific data distributions, making an effective scene-based categorization of samples necessary to improve their reliability across diverse domains. Manual captioning, though valuable, is both labor-intensive and time-consuming, creating a bottleneck in the data annotation process. Large Visual Language Models (LVLMs) present a compelling solution by automating image analysis and catego"},"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":"2501.17131","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-28T18:23:12Z","cross_cats_sorted":[],"title_canon_sha256":"bbc3ddefbcc689668a3bb07a74c0fb48a1a16adbb3faac00b2f1d7532e8823a4","abstract_canon_sha256":"c0a6fb9c55fcfa6f18e926f01036f4174b6295d20660627649c1570b0cc3d46e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:16.689755Z","signature_b64":"ea7o2mzqTBiRewWbdc04saGiwAVLovhRlLc9Hv0y6LajungupG/mvCdqEIPrY3puK99naK8eFz/zxUzMvx4ABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8596796c28ee3d5c321bfa41c429ed2cf2357b8405343e631ec596dd87ebc9","last_reissued_at":"2026-07-05T10:45:16.689255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:16.689255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scenario Understanding of Traffic Scenes Through Large Visual Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Esteban Rivera, Jannik L\\\"ubberstedt, Markus Lienkamp, Nico Uhlemann","submitted_at":"2025-01-28T18:23:12Z","abstract_excerpt":"Deep learning models for autonomous driving, encompassing perception, planning, and control, depend on vast datasets to achieve their high performance. However, their generalization often suffers due to domain-specific data distributions, making an effective scene-based categorization of samples necessary to improve their reliability across diverse domains. Manual captioning, though valuable, is both labor-intensive and time-consuming, creating a bottleneck in the data annotation process. Large Visual Language Models (LVLMs) present a compelling solution by automating image analysis and catego"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17131","kind":"arxiv","version":2},"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/2501.17131/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":"2501.17131","created_at":"2026-07-05T10:45:16.689312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17131v2","created_at":"2026-07-05T10:45:16.689312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17131","created_at":"2026-07-05T10:45:16.689312+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6CZM6LMFDXD","created_at":"2026-07-05T10:45:16.689312+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6CZM6LMFDXD2XBS","created_at":"2026-07-05T10:45:16.689312+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6CZM6LM","created_at":"2026-07-05T10:45:16.689312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.05442","citing_title":"Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6CZM6LMFDXD2XBSDP5EDRBJ5U","json":"https://pith.science/pith/H6CZM6LMFDXD2XBSDP5EDRBJ5U.json","graph_json":"https://pith.science/api/pith-number/H6CZM6LMFDXD2XBSDP5EDRBJ5U/graph.json","events_json":"https://pith.science/api/pith-number/H6CZM6LMFDXD2XBSDP5EDRBJ5U/events.json","paper":"https://pith.science/paper/H6CZM6LM"},"agent_actions":{"view_html":"https://pith.science/pith/H6CZM6LMFDXD2XBSDP5EDRBJ5U","download_json":"https://pith.science/pith/H6CZM6LMFDXD2XBSDP5EDRBJ5U.json","view_paper":"https://pith.science/paper/H6CZM6LM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17131&json=true","fetch_graph":"https://pith.science/api/pith-number/H6CZM6LMFDXD2XBSDP5EDRBJ5U/graph.json","fetch_events":"https://pith.science/api/pith-number/H6CZM6LMFDXD2XBSDP5EDRBJ5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6CZM6LMFDXD2XBSDP5EDRBJ5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6CZM6LMFDXD2XBSDP5EDRBJ5U/action/storage_attestation","attest_author":"https://pith.science/pith/H6CZM6LMFDXD2XBSDP5EDRBJ5U/action/author_attestation","sign_citation":"https://pith.science/pith/H6CZM6LMFDXD2XBSDP5EDRBJ5U/action/citation_signature","submit_replication":"https://pith.science/pith/H6CZM6LMFDXD2XBSDP5EDRBJ5U/action/replication_record"}},"created_at":"2026-07-05T10:45:16.689312+00:00","updated_at":"2026-07-05T10:45:16.689312+00:00"}