{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NFQGSUZHHEVSOAJQ2ZMV4OX5RD","short_pith_number":"pith:NFQGSUZH","canonical_record":{"source":{"id":"2506.02615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T08:32:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3874df998b930e583ea520235ace162e48a38fa8c739ad0991206e8d2b2f6d66","abstract_canon_sha256":"f1fa288e5bc7604e028831db0c04d6732ef3169300ae8029da311bf47b5eadd0"},"schema_version":"1.0"},"canonical_sha256":"6960695327392b270130d6595e3afd88c7da0625956dc05bb1ab20b2f25298f2","source":{"kind":"arxiv","id":"2506.02615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02615","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02615v1","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02615","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"NFQGSUZHHEVS","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"NFQGSUZHHEVSOAJQ","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"NFQGSUZH","created_at":"2026-07-05T11:15:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NFQGSUZHHEVSOAJQ2ZMV4OX5RD","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T08:32:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3874df998b930e583ea520235ace162e48a38fa8c739ad0991206e8d2b2f6d66","abstract_canon_sha256":"f1fa288e5bc7604e028831db0c04d6732ef3169300ae8029da311bf47b5eadd0"},"schema_version":"1.0"},"canonical_sha256":"6960695327392b270130d6595e3afd88c7da0625956dc05bb1ab20b2f25298f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:05.397687Z","signature_b64":"GHulmWmKlVdj41fpzFAE+d4d/CFLh+PU2upllsHiwGhxQSaMtZQ//PJNhmWUaii7pPYV91C6/o2oVxUI4dGiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6960695327392b270130d6595e3afd88c7da0625956dc05bb1ab20b2f25298f2","last_reissued_at":"2026-07-05T11:15:05.397187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:05.397187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02615","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sz4rvFUPHaYM+1/IsOQfUyycYlzUYBl8w+HmbrCPa8vVxMGUjdujRtvbezbHlRoDD7gBA+YvaJFdntvd9mo2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:01:55.649964Z"},"content_sha256":"6ef91acfc62fa16d6c21c47d010fa5e2f5a9762eb34ee36c16561112af81e4a7","schema_version":"1.0","event_id":"sha256:6ef91acfc62fa16d6c21c47d010fa5e2f5a9762eb34ee36c16561112af81e4a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NFQGSUZHHEVSOAJQ2ZMV4OX5RD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Question-Answering for Driving Scene Understanding Using Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Seog Han, Minjin Baek, Safaa Abdullahi Moallim Mohamud","submitted_at":"2025-06-03T08:32:43Z","abstract_excerpt":"In this paper, we present a hierarchical question-answering (QA) approach for scene understanding in autonomous vehicles, balancing cost-efficiency with detailed visual interpretation. The method fine-tunes a compact vision-language model (VLM) on a custom dataset specific to the geographical area in which the vehicle operates to capture key driving-related visual elements. At the inference stage, the hierarchical QA strategy decomposes the scene understanding task into high-level and detailed sub-questions. Instead of generating lengthy descriptions, the VLM navigates a structured question tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02615","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/2506.02615/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gl99r9GpweOKL7XfaSE/clqbtms0BreivxE0xZzEYB6ypfXmlpj4A01O6qB981yWIn0hxL0P3wOHbrW83Tj3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:01:55.650500Z"},"content_sha256":"a75cd7e22700c2034003d35d3aa66465706227edf6251380515022f392fa2d84","schema_version":"1.0","event_id":"sha256:a75cd7e22700c2034003d35d3aa66465706227edf6251380515022f392fa2d84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFQGSUZHHEVSOAJQ2ZMV4OX5RD/bundle.json","state_url":"https://pith.science/pith/NFQGSUZHHEVSOAJQ2ZMV4OX5RD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFQGSUZHHEVSOAJQ2ZMV4OX5RD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T17:01:55Z","links":{"resolver":"https://pith.science/pith/NFQGSUZHHEVSOAJQ2ZMV4OX5RD","bundle":"https://pith.science/pith/NFQGSUZHHEVSOAJQ2ZMV4OX5RD/bundle.json","state":"https://pith.science/pith/NFQGSUZHHEVSOAJQ2ZMV4OX5RD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFQGSUZHHEVSOAJQ2ZMV4OX5RD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NFQGSUZHHEVSOAJQ2ZMV4OX5RD","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":"f1fa288e5bc7604e028831db0c04d6732ef3169300ae8029da311bf47b5eadd0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T08:32:43Z","title_canon_sha256":"3874df998b930e583ea520235ace162e48a38fa8c739ad0991206e8d2b2f6d66"},"schema_version":"1.0","source":{"id":"2506.02615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02615","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02615v1","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02615","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"NFQGSUZHHEVS","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"NFQGSUZHHEVSOAJQ","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"NFQGSUZH","created_at":"2026-07-05T11:15:05Z"}],"graph_snapshots":[{"event_id":"sha256:a75cd7e22700c2034003d35d3aa66465706227edf6251380515022f392fa2d84","target":"graph","created_at":"2026-07-05T11:15:05Z","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/2506.02615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a hierarchical question-answering (QA) approach for scene understanding in autonomous vehicles, balancing cost-efficiency with detailed visual interpretation. The method fine-tunes a compact vision-language model (VLM) on a custom dataset specific to the geographical area in which the vehicle operates to capture key driving-related visual elements. At the inference stage, the hierarchical QA strategy decomposes the scene understanding task into high-level and detailed sub-questions. Instead of generating lengthy descriptions, the VLM navigates a structured question tr","authors_text":"Dong Seog Han, Minjin Baek, Safaa Abdullahi Moallim Mohamud","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T08:32:43Z","title":"Hierarchical Question-Answering for Driving Scene Understanding Using Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02615","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":"sha256:6ef91acfc62fa16d6c21c47d010fa5e2f5a9762eb34ee36c16561112af81e4a7","target":"record","created_at":"2026-07-05T11:15:05Z","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":"f1fa288e5bc7604e028831db0c04d6732ef3169300ae8029da311bf47b5eadd0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T08:32:43Z","title_canon_sha256":"3874df998b930e583ea520235ace162e48a38fa8c739ad0991206e8d2b2f6d66"},"schema_version":"1.0","source":{"id":"2506.02615","kind":"arxiv","version":1}},"canonical_sha256":"6960695327392b270130d6595e3afd88c7da0625956dc05bb1ab20b2f25298f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6960695327392b270130d6595e3afd88c7da0625956dc05bb1ab20b2f25298f2","first_computed_at":"2026-07-05T11:15:05.397187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:05.397187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GHulmWmKlVdj41fpzFAE+d4d/CFLh+PU2upllsHiwGhxQSaMtZQ//PJNhmWUaii7pPYV91C6/o2oVxUI4dGiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:05.397687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ef91acfc62fa16d6c21c47d010fa5e2f5a9762eb34ee36c16561112af81e4a7","sha256:a75cd7e22700c2034003d35d3aa66465706227edf6251380515022f392fa2d84"],"state_sha256":"c0271b8ee85f44487978600f1d0194d01757acd9f7c9115f444b4fe59cf7f670"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zBk4Po50g2gvjLiRHhmrkmFmvP6tKdTK9VnRqN6fEurXa41qsTXSYDZK45IftRpX1954nz9bApplV4Q29+UFDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:01:55.654757Z","bundle_sha256":"141d9f439c8cf1739ce3003635f6130ec086865d9d4fcffe136764b3258bb386"}}